Search Results

Empowering Women in Machine Learning: Amplifying Achievements, Elevating Voices, Building Leaders, and Bridging Gaps to enhance the experience of women in machine learning. 17th Women in Machine Learning Workshop (WiML 2022) The Workshop is co-located with NeurIPS on Monday, November 28th, 2022 at the New Orleans Convention Center in Louisiana, USA. Speakers Logistics Program Call for Participation Committee FAQ Code Of Conduct Machine learning is one of the fastest growing areas of computer science research. Search engines, text mining, social media analytics, face recognition, DNA sequence analysis, speech and handwriting recognition, healthcare analytics are just some of the applications in which machine learning is routinely used. In spite of the wide reach of machine learning and the variety of theory and applications, it covers, the percentage of female researchers is lower than in many other areas of computer science. Most women working in machine learning rarely get the chance to interact with other female researchers, making it easy to feel isolated and hard to find role models. The annual Women in Machine Learning Workshop is the flagship event of Women in Machine Learning. This technical workshop gives female faculty, research scientists, and graduate students in the machine learning community an opportunity to meet, network and exchange ideas, participate in career-focused panel discussions with senior women in industry and academia and learn from each other. Underrepresented minorities and undergraduates interested in machine learning research are encouraged to attend. We welcome all genders; however, any formal presentations, i.e. talks and posters, are given by women. We strive to create an atmosphere in which participants feel comfortable to engage in technical and career-related conversations. Now in its 17th year, the 2022 workshop is co-located in-person with NeurIPS 2022 at New Orleans in Louisiana. Besides this annual workshop, Women in Machine Learning also organizes events such as lunch at ICML and AAAI conferences, maintains a public directory of women active in ML, profiles the research of women in ML, and maintains a list of resources for women working in ML. Invited Speakers Alice Oh KAIST University Hima Lakkaraju Harvard University Bianca Zadrozny IBM Research Raesetje Sefala Distributed AI Research Institute Location The in-person workshop will be co-located with NeurIPS in New Orleans, Louisiana on Monday, November 28th, 2022 . Poster Dimensions In person event: Please pay attention to the dimensions of your posters. Workshop posters should be printed on thin paper, not laminated and no larger than 24 inches wide x 36 inches high. See more info regarding workshop poster dimensions here . Virtual event: (details coming soon) Childcare NeurIPS is kindly providing free onsite childcare to participants this year. Registration to the NeurIPS conference is required to participate in this year's WiML workshop. For more information on how to register for the childcare service, please visit the NeurIPS website. Information for authors Authors may find information about poster preparation and upload here . We are looking forward to welcoming you! Head over to our program webpage to check the list of speakers! In order to attend our event, you complete both steps below: Register to NeurIPS 2022 here . To attend our in-person event, you need to register either for the NeurIPS “Conference” or Workshops” session. Registering for either physical component will grant you access to WiML . If you are attending virtually, the NeurIPS “Virtual Only Pass” will suffice. Early registration (with reduced rates) ends on October the 14th. Information about visa application, including visa letter invitation can be found here . Fill in our WiML registration form (free) here . This form helps us keep a headcount. Authors, co-authors and volunteers will be receiving promo codes by email. Authors and co-authors of accepted abstracts, area chairs and volunteers, should have already received promo-codes they may add during the Eventbrite registration. Note: Any physical (in-person) registration includes the NeurIPS ‘Virtual Only Pass’ and as such provides a pass to our virtual component too. Attendees that are attending only virtually using the NeurIPS “Virtual Only Pass” registration, they will be able to access the livestream links of our in-person event. PROGRAM PANELISTS MENTORSHIP ROUNDTABLES LIST OF ACCEPTED POSTERS LIST OF REVIEWERS Monday, November 28, 2022 [in-person] (Time in CT) Morning Session 7:30 am - 8:30 am Registration & Breakfast 8:30 am - 8:45 am Opening Remarks - Konstantina Palla (Senior Program Chair) 8:45 am - 9:00 am D&I Chair remarks - Danielle Belgrave 9:00 am - 9:10 am Contributed talk (Tejaswi Kasarla ) - "Maximum Class Separation as Inductive Bias in One Matrix" 9:10 am - 9:20 am Contributed talk (Taiwo Kolajo ) - "Pre-processing of Social Media Feeds based on Integrated Local Knowledge Base" 9:20 am - 9:55 am Invited talk - Alice Oh - "The importance of multiple languages and multiple cultures in NLP research" 9:55 am - 10:10 am Coffee break 10:10 am - 10:25 am WiML Board Remarks - Jessica Schrouff 10:25 am - 11:00 am Invited talk - Raesetje Sefala - "Constructing visual datasets to answer research questions" 11:00 am - 11:10 am Contributed talk (Pascale Gourdeau ) - "When are Local Queries Useful for Robust Learning?" 11:10 am - 11:20 am Contributed talk (Annie S Chen ) - "You Only Live Once: Single-Life Reinforcement Learning" 11:20 am - 1:20 pm Mentorship roundtables & Lunch - Mentors: Adam Roberts, Stephanie Hyland, Bianca Zadrozny, Sima Behpour, Mercy Asiedu, Franziska Boenisch, Eleni Triantafillou, Isabela Albuquerque, Yisong Yue, Amy Zhang, Zelda Mariet, Tristan Naumann, Danielle Belgrave, Shakir Mohamed, Tong Sun, Gintare Karolina Dziugaite, Samy Bengio, Rianne van den Berg, Maja Rudolph, Luisa Cutillo, Ioana Bica, Clara Hu, Rosanne Liu, Jennifer Wei, Alice Oh, SueYeon Chung, Erin Grant, Sasha Luccioni, Michela Paganini, Mounia Lalmas-Roelke, Claire Vernade, Alekh Agarwal, Neema Mduma, Vinod Prabhakaran, Savannah Thais, Jonathan Frankle, Ce Zhang, Rose Yu, Jessica Schrouff, Bo Li, Katherine Heller, Ben Poole, Setareh Ariafar, Christina Pavlopoulou, Isabel Morlidge, Kavya Srinet, Cheng Zhang, Elise van der Pol, Diana Montanes, Lise Diagne, Le Yu, Megan Forrester. Afternoon Session 1:20 pm - 1:55 pm Invited talk - Bianca Zadrozny - "Machine Learning for Climate Risk" 1:55 pm - 2:05 pm Contributed talk (Elizabeth Bondi-Kelly) - "Human-AI Interaction in Selective Prediction Systems" 2:05 pm - 2:15 pm Contributed talk (Gowthami Somepalli) - "Investigating Reproducibility from the Decision Boundary Perspective." 2:15 pm - 2:35 pm Coffee break 2:35 pm - 3:10 pm Invited talk -Hima Lakkaraju - "A Brief History of Explainable AI: From Simple Rules to Large Pretrained Models" 3:10 pm - 4:10 pm Panel discussi on 4:10 pm - 4:20 pm Closing Remarks 4:20 pm - 4:30 pm Poster setup 4:30 pm - 6:00 pm Joint Affinity Groups Poster Session Monday, December 5, 2022 [virtual] (Time in ET) 9:30 am - 9:40 am Opening Remarks 9:40 am - 9:55 am Contributed talk (Okechinyere J Achilonu ) - "Natural language processing for automated information extraction of cancer parameters from free-text pathology reports" 9:55 am - 10:10 am Contributed talk (Paula Harder ) - "Physics-Constrained Deep Learning for Climate Downscaling" 10:10 am - 10:25 am Contributed talk (Silvia Tulli ) - "Explanation-Guided Learning for Human-AI collaboration" 10:25 am - 10:40 am Contributed talk (Mina Ghadimi Atigh ) - "Hyperbolic Image Segmentation" 10:40 am - 10:50 am Set up (for mentorship session) 10:50 am - 11:50 am Mentorship Panel (Discussion + Q&A) with Jenn Wortman Vaughan (Microsoft Research), Colin Raffel (University of North Carolina) Kristen Grauman (University of Texas at Austin) 11:50 am - 12:00 pm Break 12:00 pm - 12:35 pm Sponsor Talks 2:00 pm - 4:00 pm Joint Affinity Groups Poster Session Alice Oh KAIST University Hima Lakkaraju Harvard University Bianca Zadrozny IBM Research Raesetje Sefala Distributed AI Research Institute Rianne van den Berg Microsoft Research AI and Creativity: Adam Roberts (Google Brain) Choosing between Academia and Industry: Stephanie Hyland (Microsoft Research) and Bianca Zadrozny (IBM Research) Continual Learning & Open-World Learning: Sima Behpour (Bosch) Founding and Funding Startups: Mercy Asiedu (Google) Gender-related challenges: Franziska Boenisch (Vector Institute) Generalization & Robustness: Eleni Triantafillou (Google Brain) and Isabela Albuquerque (DeepMind) Getting a job (academia): Yisong Yue (Caltech) and Amy Zhang (UT Austin) Getting a job (industry): Zelda Mariet (Google) Healthcare/clinical applications: Danielle Belgrave (DeepMind) and Tristan Naumann (Microsoft Research) Leadership: Shakir Mohamed (DeepMind) and Tong Sun (Adobe) Learning theory: Karolina Dziguaite (Google Brain) Life in industry research: Samy Bengio (Apple) and Rianne van den Berg (Microsoft Research) Life with kids: Maja Rudolph (BCAI) and Luisa Cutillo (University of Leeds) Mental health & surviving in grad school: Ioana Bica (DeepMind), Clara Hu (Google Brain), and Rosanne Liu (Google Brain) ML for Science: Jennifer Wei (Google) Natural language processing: Alice Oh (KAIST) Negotations in ML: Nicole Bannon (81cents) Neuroscience & cognitive science: Erin Grant (UCL), SueYeon Chung (NYU/Flatiron Institute), and Noga Zaslavsky Non-traditional paths in machine learning: Sasha Luccioni (HuggingFace) and Michela Paganini (DeepMind) Recommender systems: Mounia Lalmas-Roelke (Spotify) Reinforcement learning: Claire Vernade (DeepMind), Alekh Agarwal (Google), and Elise van der Pol (Microsoft Research) Seeking funding in academia: Neema Mduma (The Nelson Mandela African Institution of Science and Technology) Social science applications: Vinod Prabhakaran (Google Research), Savannah Thais (Columbia University), and Sarah Brown (University of Rhode Island) Systems and machine learning: Jonathan Frankle (Harvard University/MosaicML) and Ce Zhang (ETH Zurich) Time Series: Rose Yu (UCSD) Trustworthy machine learning: Jessica Schrouff (DeepMind), Bo Li (UIUC), and Katherine Heller (Google Research) ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier That Validates 301 New Exoplanets Noa Lubin (Bar-Ilan University)* When are Local Queries Useful for Robust Learning? Pascale Gourdeau (University of Oxford)*; Varun Kanade (University of Oxford); Marta Kwiatkowska (Oxford University); James Worrell (University of Oxford) Natural language processing for automated information extraction of cancer parameters from free-text pathology reports Okechinyere J Achilonu (University of the Witwatersrand)* Discriminative Candidate Selection for Image Inpainting Lucia Cipolina-Kun (University of Bristol)*; Simone Caenazzo (Riskcare); Sergio Manuel S Papadakis (Konfío) Determination of Neural Network Parameters for Path Loss Prediction in Very High Frequency Wireless Channel Abigail O Jefia (Cisco Systems)*; Segun Popoola (Manchester Metropolitan University); Aderemi A. Atayero (Covenant University) Development of predictive model for survival of paediatric HIV/AIDS patients in south western Nigeria using data mining techniques Agbelusi Olutola (Rufus Giwa Polytechnic )* Modelling non-reinforced preferences using selective attention Noor Sajid (University College London)*; Panagiotis Tigas (Oxford University); Zafeirios Fountas (Huawei Technologies); Qinghai Guo (Huawei Technologies); Alexey Zakharov (Huawei Technologies); Lancelot Da Costa (Imperial College London) Data Analysis and Machine Learning for Speech Music Playlist Generation Maikey Zaki Khorani (Salahaddin University/College of Engineering)* Meta Optimal Transport Brandon Amos (Facebook AI Research); Samuel Cohen (University College London); Giulia Luise (University College London)*; Ievgen Redko (Aalto University) Single-modality and joint fusion deep learning for diabetic retinopathy diagnosis Sara EL-ATEIF (ENSIAS)*; Ali Idri (University Mohamed V) Multi-Armed Bandit Problem with Temporally-Partitioned Rewards Giulia Romano (Politecnico di Milano)*; Andrea Agostini (Politecnico di Milano); Francesco Trovò (Politecnico di Milano); Nicola Gatti (Politecnico di Milano); Marcello Restelli (Politecnico di Milano) The use of Region-based Convolutional Neural Network Model for Analysing Unmanned Aerial Vehicle Remote Sensing Odunayo E Oduntan (Chrisland University Abeokuta, Nigeria)* Kernel Density Bayesian Inverse Reinforcement Learning Aishwarya Mandyam (Stanford University)*; Didong Li (University of North Carolina); Diana Cai (Princeton University); Andrew Jones (Princeton University Department of Computer Science); Barbara Engelhardt (Stanford University) Multimodal Checklists for Fair Clinical Decision Support Qixuan Jin (Massachusetts Institute of Technology)*; Marzyeh Ghassemi (University of Toronto) Investigating Reproducibility from the Decision Boundary Perspective Gowthami Somepalli (University of Maryland, College Park)*; Arpit Bansal (University of Maryland - College Park); Liam Fowl (University of Maryland); Ping-yeh Chiang (University of Maryland, College Park); Yehuda Dar (Rice University); Richard Baraniuk (Rice University); Micah Goldblum (University of Maryland); Tom Goldstein (University of Maryland, College Park) Development of a modified likelihood ratio model for handwriting identification in forensic science Adeyinka O Abiodun (National Open University of Nigeria)*; Sesan Adeyemo (University of Ibadan); Adegboyega Adebayo (National Open University of Nigeria) Self-Supervised Graph Representation Learning for chip design-partitioning on multi-FPGA platforms Divyasree Tummalapalli (Intel Corporation)*; Chiranjeevi Kunapareddy (Intel Corporation); Vikas Akalwadi (Intel Corporation); Rahul Govindan (Intel Corporation); Balaji G (Intel Corporation) Hierarchically Clustered PCA and CCA via a Convex Clustering Penalty Amanda M Buch (Weill Cornell Medicine, Cornell University)*; Conor Liston (Weill Cornell Medicine, Cornell University); Logan Grosenick (Weill Cornell Medicine, Cornell University) Deep Metric Learning to predict cardiac pressure with ECG Hyewon Jeong (MIT)*; Marzyeh Ghassemi (University of Toronto, Vector Institute); Collin Stultz (MIT) Spatial clustering with random partitions on ovarian cancer data Yunshan Duan (University of Texas at Austin)*; Peter Mueller (University of Texas); Wenyi Wang (MD Anderson); Shuai Guo (MD Anderson) Object Segmentation of Cluttered Airborne LiDAR Point Clouds Mariona Carós (Universitat de Barcelona)*; Ariadna Just (Institut Cartogràfic i Geològic de Catalunya); Santi Seguí (Universitat de Barcelona); Jordi Vitria (Universitat de Barcelona) Identifying Disparities in Sepsis Treatment using Inverse Reinforcement Learning Hyewon Jeong (MIT)*; Taylor W Killian (University of Toronto, Vector Institute); Sanjat Kanjilal (Harvard Medical School); Siddharth Nagar Nayak (Massachusetts Institute of Technology); Marzyeh Ghassemi (University of Toronto, Vector Institute) Multi Mix Mask – RCNN (M3RCNN) for Instance Intervertebral Disc Segmentation Malinda Vania (Ulsan National Institute of Science and Technology)*; Lim Sunghoon (Ulsan National Institute of Science and Technology) The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneck Chen Shani (The Hebrew university of Jerusalem)*; Jonathan Zarecki (Bar-Ilan University); Dafna Shahaf (The Hebrew University of Jerusalem) Towards an automatic classification for software requirements written in Spanish María Isabel Limaylla Lunarejo (Universidade da Coruña)* Exploiting Pretrained Biochemical Language Models for Targeted Drug Design Gökçe Uludoğan (Bogazici University)*; Arzucan Özgür (Bogazici University); Elif Ozkirimli (Roche AG); Kutlu Ülgen (Bogazici University ); Nilgün Karalı (Istanbul University) Curriculum learning for improved femur fracture classification: scheduling data with prior knowledge and uncertainty Amelia Jiménez-Sánchez (IT University of Copenhagen)*; Diana Mateus (Centrale Nantes); Sonja Kirchhoff (TUM school of medicine); Chlodwig Kirchhoff (TUM school of medicine); Peter Biberthaler (TUM school of medicine); Nassir Navab ("TU Munich, Germany"); Miguel Angel González Ballester (Universitat Pompeu Fabra); Gemma Piella (Pompeu Fabra University) Shortcuts in Public Medical Image Datasets Amelia Jiménez-Sánchez (IT University of Copenhagen)*; Andreas Skovdal (ITU); Frederik Bechmann Faarup (ITU); Kasper Thorhauge Grønbek (ITU); Veronika Cheplygina (ITU) Adaptively Identifying Patient Populations With Treatment Benefit in Clinical Trials Alicia Curth (University of Cambridge)*; Alihan Hüyük (University of Cambridge); Mihaela van der Schaar (University of Cambridge) Improving Robustness to Distribution Shift with Methods from Differential Privacy Neha Hulkund (MIT)* Quantifying Gender Bias in Hindi Language Models Neeraja Kirtane (Manipal Institute of Technology)*; V Manushree (Manipal Institute Of Technology); Aditya Kane (Pune Institute of Computer Technology) De novo PROTAC design using graph-based deep generative models Divya V Nori (Massachusetts Institute of Technology)*; Connor Coley (MIT); Rocio Mercado (Massachusetts Institute of Technology) Self-Contained Entity Discovery from Captioned Videos Melika ayoughi (university of amsterdam)*; Paul Groth (University of Amsterdam); Pascal Mettes (University of Amsterdam) Reduce False Negative in Distant supervised learning using Dependency tree-LSTM to Construct a Knowledge Graph Samira Korani (NUIG)*, John McCrae (NUIG) Break the bottleneck of AI deployment at the edge. Paula Ramos (Intel)*; Helena Kloosterman (Intel); Samet Akcay (Intel); Yu-Chun Liu (Intel Corp.); Raymond Lo (Intel) Towards probabilistic end-to-end Deep Learning Weather Forecasting: Spatio-Temporal Temperature Forecasting using Normalizing Flows Christina Winkler (Technical University of Munich)* Bias Assessment of Text-to-Image Models Sasha Luccioni (Mila)*; Clementine Fourrier (Hugging Face); Nathan Lambert (Hugging Face); Unso Eun Seo Jo (Hugging Face); Irene Solaiman (Hugging Face); Helen Ngo (Hugging Face); Nazneen Rajani (Hugging Face); Giada Pistilli (Hugging Face); Yacine Jernite (Hugging Face); Margaret Mitchell (Hugging Face) SO(3) Equivariant Framework for Spatial Networks Sarp Aykent (Auburn University); Tian Xia (Auburn University)* Protein Structure Ranking with Atom-level Geometric Representation Learning Tian Xia (Auburn University)*; Sarp Aykent (Auburn University) Detecting Synthetic Opioids with NQR Spectroscopy and Complex-Valued Signal Denoising Amber J Day (Los Alamos National Laboratory)*; Natalie Klein (Los Alamos National Laboratory); Michael Malone (Los Alamos National Laboratory); Harris Mason (Los Alamos National Laboratory); Sinead A Williamson (UT Austin) Identifying fine climatic parameters for high maize yield using pattern mining: case study from Benin (West Africa) Souand Peace Gloria TAHI (University of Abomey-Calavi)*; Vinasetan Ratheil Houndji (Institut de Formation et de Recherche en Informatique, University of Abomey-Calavi); Castro Hounmenou (Laboratoire de Biomathématiques et d’Estimations Foresti`eres, Faculty of Agronomic Sciences, University of Abomey-Calavi); Romain Glèlè Kakaï (Laboratoire de Biomathématiques et d’Estimations Foresti`eres, Faculty of Agronomic Sciences, University of Abomey-Calavi) GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks Kenza Amara (ETH Zurich)*; Rex Ying (Yale University); Ce Zhang (ETH) Using Visual Similarity to Navigate eCommerce Inventory Shubhangi Tandon (ebay inc)*; Christopher Miller (ebay inc); Selcuk Kopru (ebay); Senthilkumar Gopal (ebay inc) Mixture of Gaussian Processes with Probabilistic Circuits for Multi-Output Regression Mingye Zhu (University of Science and Technology of China)*; Zhongjie Yu (TU Darmstadt); Martin Trapp (Aalto University ); Arseny Skryagin (TU Darmstadt); Kristian Kersting (TU Darmstadt) Synthetic Data Augmentation for Time Series Forecasting Kasumi Ohno (Toyota Technological Institute)*; Kohei Makino (Toyota Technological Institute ); Makoto Miwa (Toyota Technological Institute); Yutaka Sasaki (Toyota Technological Institute) Task-conditioned modelling of drug-target interactions Emma Petersson Svensson (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria)*; Pieter-Jan Hoedt (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Sepp Hochreiter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Guenter Klambauer (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) Can deep learning models understand natural language descriptions of patient symptoms following cataract surgery? Mohita Chowdhury (Ufonia Limited)*; Oliver Gardiner (Ufonia Limited); Ernest Lim (Ufonia Limited); Aisling Higham (Ufonia Limited); Nick de Pennington (Ufonia Limited) Hyperbolic Image Segmentation Mina Ghadimi Atigh (University of Amsterdam)*; Julian M Schoep (Promaton); Erman Acar (Vrije Universiteit Amsterdam); Nanne van Noord (University of Amsterdam); Pascal Mettes (University of Amsterdam) Maximum Class Separation as Inductive Bias in One Matrix Tejaswi Kasarla (University of Amsterdam)*; Gertjan Burghouts (TNO); Max van Spengler (University of Amsterdam); Elise van der Pol (Microsoft Research); Rita Cucchiara (Università di Modena e Reggio Emilia); Pascal Mettes (University of Amsterdam) CLOOME: Contrastive Learning for Molecule Representation with Microscopy Images and Chemical Structures Ana Sanchez-Fernandez (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria)*; Elisabeth Rumetshofer (JKU Linz); Sepp Hochreiter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Guenter Klambauer (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) Boosting Multi-modal Contrastive Learning with Modern Hopfield Networks and InfoLOOB Andreas Fürst (JKU Linz); Elisabeth Rumetshofer (JKU Linz)*; Johannes Lehner (Johannes Kepler University); Viet T. Tran (Johannes Kepler University Linz); Fei Tang (Here Technologies); Hubert Ramsauer (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); David Kreil (Institute of Advanced Research in Artificial Intelligence (IARAI) GmbH); Michael K Kopp (Institute of Advanced Research in Artificial Intelligence (IARAI) GmbH); Guenter Klambauer (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Angela Bitto-Nemling (JKU); Sepp Hochreiter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) Global-based Deep Q-Network for Molecule Generation Asmaa Rassil (Faculty of science, University Chouaib Doukkali)*; Hiba Chougrad (University Sidi Mohamed Ben Abdellah); Hamid Zouaki (university Chouaib Doukkali) A Semantically Conditioned Code-Mixed Natural Language Generation for Task-Oriented Dialog Suman Dowlagar (International Institute of Information Technology-Hyderabad)*; Radhika Mamidi (IIIT Hyderabad) Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting Chandana Priya Nivarthi (University of Kassel)*; Stephan Vogt (University of Kassel); Bernhard Sick (University of Kassel) Modern Hopfield Networks for Iterative Learning on Tabular Data Bernhard Schäfl (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Lukas Gruber (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Angela Bitto-Nemling (JKU)*; Sepp Hochreiter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) Delirium Prediction using Long Short-Term Memory (LSTM) in the Electronic Health Record Siru Liu (Vanderbilt University Medical Center)*; Joseph Schlesinger (Department of Anesthesiology, Division of Critical Care Medicine, Vanderbilt University Medical Center); Allison McCoy (Department of Biomedical Informatics, Vanderbilt University Medical Center); Thomas Reese (Department of Biomedical Informatics, Vanderbilt University Medical Center); Bryan Steitz (Department of Biomedical Informatics, Vanderbilt University Medical Center); Elise Russo (Department of Biomedical Informatics, Vanderbilt University Medical Center); Adam Wright (Department of Biomedical Informatics, Vanderbilt University Medical Center) Evaluating and Improving Robustness of Self-Supervised Representations to Spurious Correlations Kimia Hamidieh (University of Toronto, Vector Institute)*; Haoran Zhang (MIT); Marzyeh Ghassemi (University of Toronto, Vector Institute) FACTORS INFLUENCING POSTGRADUATE STUDENTS' ACADEMIC PERFORMANCE: MACHINE LEARNING APPROACH. Ayodele Esther Awokoya (University of ibadan)* A Simple Phoneme-based Error Simulator for ASR Error Correction Mohita Chowdhury (Ufonia Limited)*; Oliver Gardiner (Ufonia Limited); Yishu Miao (Ufonia Limited) Deep Learning methods for biotic and abiotic stresses detection in fruits and vegetables: state of the art and perspectives Ariane Houetohossou (University of Abomey-Calavi)*; Ratheil Vinasetan HOUNDJI (2Institut de Formation et de Recherche en Informatique, University of University of Abomey-Calavi); Castro Gbêmêmali HOUNMENOU (Laboratoire de Biomathématiques et d’Estimations Forestières, Faculty of Agronomic Sciences, University of Abomey-Calavi); Rachidatou SIKIROU (Laboratoire de Défense des Cultures, Centre de Recherches Agricoles d’Agonkanmey, Institut National des Recherches Agricoles du Bénin (INRAB)); Romain Lucas GLELE KAKAÏ (Laboratoire de Biomathématiques et d’Estimations Forestières, Faculty of Agronomic Sciences, University of Abomey-Calavi) Follow the Flow: An Affective Computing Interface for the On-Line Detection of Flow Mental State Elena Sajno (Università di Pisa)*; G. Riva (Catholic University of Milan, Italy); Nicole Novielli (University of Bari) Under-Counted Tensor Completion with Neural Network-based Side Information Learner Shahana Ibrahim (Oregon State University)*; Xiao Fu (Oregon State University); Rebecca Hutchinson (Oregon State University); Eugene Seo (Brown University) Detecting State Changes in Dynamic Neuronal Networks Yiwei Gong (UT Austin)*; Sinead A Williamson (UT Austin) Learning to Defer in Ranking Systems Aparna Balagopalan (MIT)*; Haoran Zhang (MIT); Elizabeth Bondi-Kelly (MIT); Thomas Hartvigsen (MIT); Marzyeh Ghassemi (University of Toronto, Vector Institute) Categorizing Online Harassment on Twitter using Graph Convolutional Networks Mozhgan Saeidi (Stanford University)* A Domain-Oblivious Approach for Learning Concise Representations of Filtered Topological Spaces for Clustering Yu Qin (Tulane University)*; Brittany Fasy (Montana University); Carola Wenk (Tulane University); Summa Brian (Tulane University) A Recommendation System in Task-Oriented Doctor-Patient Interactions Suman Dowlagar (International Institute of Information Technology-Hyderabad)*; Radhika Mamidi (IIIT Hyderabad) Explaining Predictive Uncertainty by Looking Back at Model Explanations Hanjie Chen (University of Virginia)*; Wanyu Du (University of Virginia); Yangfeng Ji (University of Virginia) DaME: Data Mapping Engine for Financial Services Shubhi Asthana (IBM Research - Almaden)*; Ruchi Mahindru (IBM Watson Research Center) Improved Text Classification via Test-Time Augmentation Helen Lu (Massachusetts Institute of Technology (MIT))*; Divya Shanmugam (MIT); Harini Suresh (MIT); John Guttag (MIT) Model Interpretation based Sample Selection in Large-Scale Conversational Assistants Kiana Hajebi (Amazon Alexa AI)* Human-AI Interaction in Selective Prediction Systems Elizabeth Bondi-Kelly (MIT)*; RAPHAEL KOSTER (DeepMind); Hannah Sheahan (DeepMind); Martin Chadwick (DeepMInd); Yoram Bachrach; Taylan Cemgil (DeepMind); Ulrich Paquet (DeepMind); Krishnamurthy Dvijotham (DeepMind) User-interactive, On-demand Cycle-GAN-Based Super Resolution and Focus Recovery on Whole Slide Images (WSI) Huimin Zhuge (Tulane University)*; Summa Brian (Tulane University); J.Quincy Brown (Tulane University) Self Supervised Learning in Microscopy Aastha Jhunjhunwala (NVIDIA)*; Siddha Ganju (Nvidia) Machine Learning for the detection of diabetic retinopathy Francisca O Oladipo (Thomas Adewumi University)*; Taiwo Amusan (Federal University Lokoja) Topic: Building Identification In Aerial Imagery using Deep learning Proscovia Nakiranda (Stellenbosch University)* Dynamic Head Pruning in Transformers Prisha Satwani (The London School of Economics and Political Science )*; yiren zhao (University of Cambridge); Vidhi Lalchand (University of Cambridge ); Robert Mullins (University of Cambridge) Mobile-PDC: High-Accuracy Plant Disease Classification for Mobile Devices. Samiiha Nalwooga (Stockholm University)*; Henry Mutegeki (Makerere University ) CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks Sakshi Varshney (IIT Hyderabad)*; Vinay K Verma (IIT Kanpur); Srijith PK (IIT, Hyderabad, India); Piyush Rai (IIT Kanpur); Lawrence Carin Duke (CS) Modeling Sharing Time Of Fake And Real News Maya Zeng (Boise State University)*; Cooper Doe (Colorado College); Vladimir Knezevic (City College of San Francisco); Francesca Spezzano (Boise State University); Liljana Babinkostova (Boise State University) Interaction Classification with Key Actor Detection in Multi-Person Sport Videos Farzaneh Askari (University of McGill)*; Rohit Ramaprasad (Birla Institute of Technology and Science); James Clark (McGill University); Martin Levine (McGill University) Estimating Fairness in the Absence of Ground-Truth Labels Michelle Bao (Stanford University)*; Jessica Dai (UC Berkeley); Keegan Hines (Arthur AI); John Dickerson (Arthur AI) Motor Imagery ECoG Signal Classification With Optimal Selection Of Minimum Electrodes Tuga Abdelkarim Ahmed (nile center for technology research)*; Shubham Kumar (.); Ruoqi Huang (.) A Noether's theorem for gradient flow: Continuous symmetries of the architecture and conserved quantities of gradient flow Bo Zhao (University of California, San Diego)*; Iordan Ganev (Radboud University); Robin Walters (Northeastern University); Rose Yu (UC San Diego); Nima Dehmamy (IBM Research) Generating High-Quality Emotion Arcs Using Emotion Lexicons Daniela Teodorescu (University of Alberta)*; Saif Mohammad (National Research Council, Canada) Exposure Fairness in Music Recommendation Rebecca Salganik (Universite de Montreal )*; Fernando Diaz (Google); Golnoosh Farnadi (Mila, HEC Montreal, Université de Montréal) DeepWear: Towards an Automated Textiles Materials Classification using a Taxonomy-based ML Approach Shu Zhong (University College London)*; Miriam Ribul (Royal College of Art); Youngjun Cho (University College London); Marianna Obrist (University College London) Revisiting Graph Neural Network Embeddings Skye Purchase (University of Cambridge)*; yiren zhao (University of Cambridge); Robert Mullins (University of Cambridge) Estimating the Treatment Effect of Antibiotics Exposure on the Risk of Developing Anti-Microbial Resistance Hyewon Jeong (MIT)*; Kexin Yang (Harvard School of Public Health); Ziming Wei (Harvard School of Public Health); Yidan Ma (Harvard School of Public Health); Intae Moon (MIT); Sanjat Kanjilal (Harvard Medical School) Can we explain Aha! moments in artificial agents ? Ikram Chraibi Kaadoud (IMT Atlantique)*; Adrien Bennetot (Segula Technologies - Sorbonne Université - Ensta ParisTech); Barbara Mawhin (Human Factors Department, EBT-Salient Aero Foundation); Vicky Charisi (European Commission, Joint Research Center (JRC)); Natalia Diaz-Rodriguez (Department of Computer Science and Artificial Intelligence, DaSCI Andalusian Institute in Data Science and Computational Intelligence, University of Granada) Multimodal Deep Learning for Weapon Detection Parie R Desai (Marietta High School)*; Prajwal Saokar (Berry College); William Wansing (Mill Creek High School) The Role of Expert-driven Prompt Engineering for Fine-grained Zero-shot Classification in Fashion Dhanashree Balaram (Lily AI)*; Matthew Nokleby (LILY AI); Thiyagarajan Ramanathan (Lily AI); Ajitesh Gupta Gupta (Lily AI); Ravi Kannan (Lily AI) Explaining complex system of multivariate times series behavior Ikram Chraibi Kaadoud (IMT Atlantique)*; Lina Fahed (IMT Atlantique, Lab-STICC); Tian Tian (IMT Atlantique, Lab-STICC); Yannis Haralambous (IMT Atlantique); Philippe Lenca (IMT Atlantique) Computational models of Language Variation in Literary Narratives Krishnapriya Vishnubhotla (University of Toronto)* Graph Transformer Networks for Nuclear Proliferation Detection in Urban Environments Anastasiya Usenko (Pacific Northwest National Laboratory)*; Sameera Horawalavithana (Pacific Northwest National Laboratory); Ellyn Ayton (Pacific Northwest National Laboratory); Joon-Seok Kim (Pacific Northwest National Laboratory); Svitlana Volkova (Pacific Northwest National Laboratory) Automated Staging of Breast Cancer Histopathology Images Using Deep Learning. Angela M Crabtree (Providence Portland Medical Center (Earle A. Chiles Research Institute), University of Oregon)*; Narmada Naik (University Of Montreal); Kevin L Matlock (Omics Data Automation) Gaussian Process parameterized Covariance Kernels for Non-stationary Regression Vidhi Lalchand (University of Cambridge )*; Talay M Cheema (University of Cambridge); Laurence Aitchison (University of Bristol); Carl Edward Rasmussen (Cambridge University) Heart Disease Prediction Using Machine Learning Techniques Asegunloluwa E Babalola (Anchor University, Lagos)*; Tekena Solomon (Anchor University, Lagos) Multi-group Reinforcement Learning for Electrolyte Repletion Promise Osaine Ekpo (Princeton University)*; Barbara Engelhardt (Princeton University) Trading off Utility, Informativeness, and Complexity in Emergent Communication Mycal Tucker (MIT); Julie A. Shah (MIT); Roger Levy (Massachusetts Institute of Technology); Noga Zaslavsky (MIT)* Mitigating Online Grooming with Federated Learning Khaoula Chehbouni (HEC Montreal); Gilles Caporossi (HEC Montreal); Reihaneh Rabbany (McGill University)*; Martine De Cock (University of Washington Tacoma); Golnoosh Farnadi (Mila, HEC Montreal, Université de Montréal) Towards Private and Fair Federated Learning Sikha Pentyala (University of Washington, Tacoma)*; Nicola Neophytou (Mila); anderson nascimento (UW); Martine De Cock (University of Washington Tacoma); Golnoosh Farnadi (Mila, HEC Montreal, Université de Montréal) Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy Rachel Redberg (UC Santa Barbara); Yuqing Zhu (UC Santa Barbara)*; Yu-Xiang Wang (UC Santa Barbara) Characteristics of White Helmets Disinformation vs COVID-19 Misinformation Anika M Halappanavar (Pacific Northwest National Laboratory )*; Maria Glenski (Pacific Northwest National Laboratory) Biomedical Word Sense Disambiguation with Contextualized Representation Learning Mozhgan Saeidi (Stanford University)* Model Understanding and Debugging at The Level of Subpopulation Jun Yuan (New York University)* Fair Active learning by exploiting causal data structure Sindhu C M Gowda (University of Toronto)*; Haoran Zhang (MIT); Marzyeh Ghassemi (University of Toronto) Preference-Aware Constrained Multi-Objective Bayesian Optimization Alaleh Ahmadianshalchi (Washington State University)*; Syrine Belakaria (Washington State university); Janardhan Rao Doppa (Washington State University) Preliminary Study for Impact of Social Media Networks on Traffic Prediction Valeria Laynes Fiascunari (University of Central Florida)*; Luis Rabelo (University of Central Florida) Explanation-Guided Learning for Human-AI collaboration Silvia Tulli (Instituto Superior Técnico)* Trust Me Not: Trust Scoring for Continuous Model Monitoring Nandita Bhaskhar (Stanford University)*; Daniel Rubin (Stanford University); Christopher Lee-Messer (Stanford University) Multispectral Masked Autoencoder for Remote Sensing Representation Learning Yibing Wei (University of Wisconsin - Madison)*; Zhicheng Yang (PAII Inc.); Hang Zhou (PAII, Inc.); Mei Han (PAII Inc.); Pedro Morgado (University of Wisconsin-Madison); Jui-Hsin Lai (PAII Inc.) Learning Pedestrian Behaviour for Autonomous Vehicle Interactions Fanta Camara (University of Leeds)* Comparing neural population responses based on pairwise $p$-Wasserstein distance between topological signatures Liu Zhang (Princeton University)*; Fei Han (National University of Singapore); KELIN XIA (NANYANG TECHNOLOGICAL UNIVERSITY) Adversarial Analysis of Fake News Detectors Annat Koren (City College of San Francisco)*; Hunter Ireland (Boise State University); Sandra D Luo (Timberline High School); Eryn Jagelski-Buchler (Boise State University); Edoardo Serra (Boise State University); Francesca Spezzano (Boise State University) Fast Parameter Tuning for Rule-base Planners towards Human-like Driving Shu Jiang (Apollo Autonomous Driving )*; Szu-Hao Wu (Apollo Autonomous Driving) Model Averaging to Learn Bayesian Network Structures with Non-Linear Structured Representations Charupriya Sharma (University of Waterloo)* Augmenting Driver Decision-Making Using Meta-Inverse Reinforcement Learning Mayuree Binjolkar (University of Washington)*; Yana Sosnovskaya (University of Washington) Explaining black-box models in natural language through fuzzy linguistic summaries - Bipolar Disorder case study Olga Kaminska (Systems Research Institute Polish Academy of Sciences)*; Katarzyna Kaczmarek-Majer (SRI PAS) Physics-Constrained Deep Learning for Climate Downscaling Paula Harder (Fraunhofer ITWM)*; Qidong Yang (New York University); Venkatesh Ramesh (Mila); Prasanna Sattigeri (IBM Research); Alex Hernandez-Garcia (Mila - Quebec AI Institute); Campbell D Watson (IBM Reserch); Daniela Szwarcman (IBM Research); David Rolnick (McGill University, Mila) Graph Convolutional Neural Network-based Quality Assessment of Light Field Images Sana Alamgeer (Universidade de Brasilia, Brazil)* Erased text retrieval from historical palimpsest manuscripts using deep autoregressive priors Anna Starynska (Rochester Institute of Technology)*; David Messinger (Rochester Institute of Technology) Mask R-CNN model for banana diseases segmentation Neema Mduma (The Nelson Mandela African Institution of Science and Technology)*; Christian A Elinisa (The Nelson Mandela African Institution of Science and Technology) Security, IP protection, Privacy on Federated Learning and Machine Learning Edge Devices Mahdieh Grailoo (Tallinn University of Technology)* SOIL MINERAL DEFICIENCY DETECTION USING A DEEP LEARNING ALGORITHM COMMONLY KNOWN AS CONVOLUTIONAL NEURAL NETWORKS JEAN Mrs. AMUKWATSE (UTAMU)* P53 in Ovarian Cancer: Heterogenous Analysis of KeyBERT, BERTopic, PyCaret and LDAs methods Mary Adewunmi (UTAS,Hobart,Australia)*; Richard Oveh (Benson Idahosa University); Christopher Yeboah (PDM University); Solomon A Olorundare (University of Lagos); Ezeobi Peace (Mbarara University of Science and Technology ) Graph-Transformer for Cross-lingual Plagiarism Detection Oumaima Hourrane (University of Hassan II)* Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxies Shachi Deshpande (Cornell University)*; Kaiwen Wang (Cornell University); Dhruv Sreenivas (Cornell University); Zheng Li (Cornell University); Volodymyr Kuleshov (Cornell University) A recommendation system for technology intelligence based on multiplex networks Foutse Yuehgoh (African institut for mathematical sciences )* Pre-processing of Social Media Feeds based on Integrated Local Knowledge Base Taiwo Kolajo (Department of Computer Science, Federal University Lokoja, Kogi State, Nigeria)*; Olawande Daramola (CPUT, Cape Town, South Africa ); Ayodele Adebiyi (Department of Computer Science, Landmark University) Attention-Augmented ST-GCN for Efficient Skeleton-based Human Action Recognition Negar Heidari (Aarhus University)*; Alexandros Iosifidis (Aarhus University) Leveraging artificial intelligence for automatic depression detection using speech recognition. Hewitt Tusiime (Makerere University)*; Alvin Nahabwe (Makerere University ); Julius Kimuli (Makerere University); Grace Babirye (Laboremus Uganda) Shapelet Guided Counterfactual Explanation Generation for Black-Box Time Series Classifiers Tina Han (ConsumerAffairs)*; Jette Henderson (CognitiveScale) Weakly Supervised Medical Image Segmentation with Soft Labels and Noise Robust Loss Banafshe BF Felfeliyan (University of Calgary)*; Abhilash Rakkunedeth (University of Alberta); Jacob Jaremko (University of Alberta); Janet Ronsky (University of Calgary) Human trafficking detection using lockstep behaviour methods Maricarmen MA Arenas (Mila)*; reihaneh rabbany (Mila); Golnoosh Farnadi (Mila) Improving Induced Valence Recognition by Integrating Acoustic Sound Semantics in Movies Shreya G Upadhyay (National Tsing Hua University)*; Bo-Hao Su (Department of Electrical Engineering, National Tsing Hua University); Chi-Chun Lee (Department of Electrical Engineering, National Tsing Hua University) Efficient Hospital Management via Length of Stay prediction using Domain Adaptation Lyse Naomi Momo Wamba (KU Leuven)*; Nyalleng Moorosi (Google); Elaine Nsoesie (Boston University); Frank Rademakers (UZ Leuven); Bart DeMoor (KU Leuven) Reinforcement Learning for Cost to Serve Pranavi Pathakota (TCS Research)*; Kunwar Zaid (TCS Research); Hardik Meisheri (TCS Research); Harshad Khadilkar (TCS Research) Dual Channel Training of Large Action Spaces in Reinforcement Learning Pranavi Pathakota (TCS Research)*; Hardik Meisheri (TCS Research); Harshad Khadilkar (TCS Research) Robustness in Weighted Networks Luisa Cutillo (University of Leeds)*; Valeria Policastro (National Research Council); Annamaria Carissimo (National Research Council) Mapping Slums with Machine Learning and Medium-Resolution Satellite Imagery Agatha Mattos (University College Dublin)*; Michela Bertolotto (University College Dublin); Gavin McArdle (University College Dublin) Investigating the Effects of Environmental Factors on the Detection of Laryngeal Cancer from Speech Signals Using Machine Learning Mary L Paterson (University of Leeds)*; Luisa Cutillo (University of Leeds); James Moor (Leeds Teaching Hospitals NHS Trust) 3D-LatentMapper: View Agnostic Single-View Reconstruction of 3D Shapes Alara Dirik (Bogazici University)*; Pinar Yanardag (Bogazici University) Toward Qualitative Mechanical Problem-Solving using Hybrid AI Shreya Bhowmick Banerjee (Rensselaer Polytechnic Institute)*; Selmer Bringsjord (Rensselaer Polytechnic Institute); Naveen Govindarajulu (RPI) Fair Targeted Immunization with Dynamic Influence Maximization Nicola Neophytou (Mila)*; Golnoosh Farnadi (Mila, HEC Montreal, Université de Montréal) You Only Live Once: Single-Life Reinforcement Learning via Learned Reward Shaping Annie S Chen (Stanford University)*; Archit Sharma (); Sergey Levine (UC Berkeley); Chelsea Finn (Stanford) Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time Caroline Choi (Stanford University)*; Huaxiu Yao (Stanford University); Yoonho Lee (Stanford University); Pang Wei Koh (Stanford University); Chelsea Finn (Google) Probabilistic Querying of Continuous-Time Sequential Events Alex J Boyd (UC Irvine); Yuxin Chang (University of California, Irvine)*; Stephan Mandt (University of California, Irivine); Padhraic Smyth (University of California, Irvine) Resume Parsing using an ensemble of CNN, Bi-LSTM and CRF in a Hard Voting Predictive Approach Scholastica N Mallo (Nigeria Defence Academy)*; Francisca Nonyelum Ogwueleka (Department of Computer Science Nigerian Defence Academy Kaduna, Nigeria); Philip Odion (Nigeria Defence Academy); Martin Irhebhude (Nigeria Defence Academy, Kaduna) Transformers for Synthesized Speech Detection Emily Bartusiak (Purdue University)* Polynomials in Bayesian Problems Lilian Wong (Borealis AI)*; Evans Harrell (Georgia Tech) Estimating Uncertainty in Safety-Critical Deep Learning Models Oishi Deb (University of Oxford)* Adaptive Temporal Pattern Matching Sepideh Koohfar (University of New Hampshire)* Respiratory Conditions (EIPH, PLH, and Mucus) in Racehorses Allison B Fisher (Washington State University)*; Warwick Bayly (Washington State University); Sierra Shoemaker (Washington State University); Julia Bagshaw (Washington State University); Yuan Wang (Washington State University); Macarena Sanz (Washington State University) Shared Hardware, Shared Baselines: An Offline Robotics Benchmark Gaoyue Zhou (CMU)*; Victoria Dean (CMU) Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics Noga Mudrik (The Johns Hopkins University)*; Yenho Chen (Georgia Institute of Technology); Eva Yezerets (The Johns Hopkins University); Christopher J Rozell (Georgia Institute of Technology); Adam Charles (Johns Hopkins University) Probabilistic Interactive Segmentation for Medical Images Hallee E Wong (MIT)*; John Guttag (MIT); Adrian V Dalca (MIT) Evaluation of Active Learning and Domain Adaptation on Health Data Kristina Holsapple (University of Delaware)*; Haoran Zhang (MIT); Marzyeh Ghassemi (University of Toronto, Vector Institute) Towards interpretable health monitoring and service anomaly detection in the cloud Yueying Li (Cornell)*; Edward Suh (Cornell University); Christina Delimitrou (Cornell) Hearing Touch: Using Contact Microphones for Robot Manipulation Shaden N Alshammari (Massachusetts Institute of Technology)*; Victoria Dean (CMU); Tess Hellebrekers (Meta AI); Pedro Morgado (University of Wisconsin-Madison); Abhinav Gupta (Carnegie Mellon University Robotics Institute) Adapting the Function Approximation Architecture in Online Reinforcement Learning John D Martin (University of Alberta); Joseph Modayil (DeepMind); Fatima Davelouis Gallardo (University of Alberta)*; Michael Bowling (University of Alberta) FMAM: A novel Factorization Machine based Attention Mechanism for Forecasting Time Series Data Fahim T Azad (Arizona State University)* The WiML Board and Committee would like to thank all the reviewers that helped: Adriana Romero-Soriano (FAIR) Alaa Bessadok (University of Sousse, Tunisia) Amita Misra (IBM) Angelica Aviles-Rivero (University of Cambridge) Ankita Shukla (ASU) Anna Klimovskaia Susmelj (Swiss Data Science Center) Asra Aslam (Insight Centre for Data Analytics, Ireland) Beyza Ermis (Boğaziçi University) Bingshan Hu (University of Alberta) Bo Dong (Amazon) Celestine Mendler-Dünner (Max Planck Institute for Intelligent Systems, Tübingen) Claire Vernade (Deepmind) Dalin Guo (UC San Diego; Twitter, Inc.) Deepika Bablani (IBM Research) Erin Grant (UC Berkeley) Gowthami Somepalli (University of Maryland, College Park) Han Shao (Toyota Technological Institute at Chicago) Hanjie Chen (University of Virginia) Ilke Demir (Intel Corporation) Isabela Albuquerque (DeepMind) Ishita Mediratta (BITS Pilani K.K. Birla Goa Campus) Itir Onal Ertugrul (Utrecht University) Kasturi Bhattacharjee (AWS AI, Amazon) Kavya Gupta (Centralesupelec) Kuan-Ting Chen (National Taiwan University) Maria Glenski (Pacific Northwest National Laboratory) Maria Lomeli (Meta) Mayoore Jaiswal (University of Washington) Mengjiao Wang (Amazon Visual Search) Mina Ghadimi Atigh (University of Amsterdam) Minhae Kwon (Soongsil University) Naga Vara Aparna Akula (CSIR-CSIO) Natalia Efremova (Queen Mary University, London) Nesime Tatbul (Intel Labs and MIT) Niha Beig Case (Western Reserve University) Nora Hollenstein (University of Copenhagen) Obioma Pelka (University of Applied Sciences and Arts Dortmund) Ozge Nilay Yalcin (Simon Fraser University) Pascale Gourdeau (University of Oxford) Peixian Liang (University of Notre Dame) Priyadarshini Kumari (Sony AI) Rania Ibrahim (Purdue University) Sakinat Folorunso Olabisi Onabanjo university Samira Daruki (Expedia Research) Sanae Lotfi (New York University) Sandareka Wickramanayake (National University of Singapore) Sandya mannarswamy (Intel India) Sara Magliacane (University of Amsterdam) Sasha Luccioni (Mila) Shahana Ibrahim (Oregon State University) Shailee Jain (The University of Texas at Austin) Shimeng Peng (Nagoya university) Shinjini Ghosh (Massachusetts Institute of Technology) Shuai Zhang (Amazon) Sinem Aslan (Ca' Foscari University of Venice) Siru Liu (Vanderbilt University Medical Center) Sonali Agarwal (IIIT-Allahabad) Subarna Tripathi (Intel Labs) Surangika Ranathunga (University of Moratuwa) Svitlana Volkova (Pacific Northwest National Laboratory) Syrine Belakaria (Washington State university) Tania Lorido-Botran (Independent Researcher) Utkarshani Jaimini (Artificial Intelligence (AI) Institute- University of South Carolina) Veronika Cheplygina (ITU) Vidhi Lalchand (University of Cambridge) Vishwali Mhasawade (New York University) Weiyan Shi (Columbia University) Xi Rao (ETH) Xiao Zhang (T-Mobile) Xinyi Chen (Google) Xun Tang (Yelp) Yao Qin (University of California, San Diego) Yixin Wang (University of Michigan) Call for Participation The 17th Workshop for Women in Machine Learning (WiML) will be co-located with NeurIPS in New Orleans, Louisiana and will be hybrid. The NeurIPS workshop for Women in Machine Learning will be held in person on Monday November the 28th and virtually on Monday December the 5th with invited speakers, oral presentations, and posters. The event brings together members of the academic and industry research landscape for an opportunity to connect and exchange ideas, and learn from each other. There will be a mentoring session to discuss current research trends and career choices in machine learning. Underrepresented minorities and undergraduates interested in pursuing machine learning research are encouraged to participate. All presenters should be women or non-binary, and all genders are invited to attend. All submissions must abide by the WiML Code of Conduct. Submission page: https://cmt3.research.microsoft.com/WiML2022 Notification of acceptance is now sent to authors. Authors with accepted su bmissions and with a submitted travel funding application will be receiving further communication. IMPORTANT DATES August 1st, 2022 11:59pm PT – Abstract Submission Open on CMT August 26th, 2022 11:59pm PT – Abstract Submission Deadline September 1st, 2022 11:59 PT - Abstract Submission Deadline [extended] September 8th, 2022 11:59pm PT - Travel funding Application Deadline September 15th, 2022 11:59pm PT – Notification of Acceptance September 16th, 2022 11:59pm PT – Notification of Travel Funding November 21st, 2022 11:59pm PT – Registration Deadline for NeurIPS November 28th, 2022 – WiML Workshop Day (in person) December 5th, 2022 – WiML Workshop Day (virtual) SUBMISSION INSTRUCTIONS We strongly encourage students, postdocs, and researchers in all areas of machine learning who are women or non-binary to submit an abstract (1 page PDF) describing new, previously, or concurrently published research. We welcome abstract submissions in theory, methodology, as well as applications. While the presenting author need not be the first author of the work, we request that the presenting author should be woman or non-binary. Submissions will be reviewed in a double-blind setting. Authors of accepted abstracts will be asked to present their work in either a virtual or in-person poster session. A few authors will be selected to give oral presentations. There are no formal proceedings. Abstracts are non-archival: they may describe completed research or work-in-progress. Please refer to the detailed Submission Instructions . TRAVEL FUNDING Registration to the NeurIPS conference is required to participate in this year's WiML workshop. Travel funding will be available for eligible WiML participants, to help cover transportation, meals, accomodation, poster printing and/or visa application related costs. The funding amounts will depend on the geographic location of the qualified recipients and their types of needs. Travel funding recipients are required to volunteer during the WiML Workshop. To qualify, the participant must: i) be a woman or non-binary, ii) be the presenting and primary author of an accepted abstract at WiML 2022, and iii) be a student, postdoc, or hold an equivalent position (equivalent positions include unemployed recent grads and early career researchers from underrepresented geographical areas). WiML travel funding is administered as reimbursements after the workshop and no funding is allocated before the workshop. If you are attending NeurIPS, we also encourage you to apply for NeurIPS’ volunteering and travel funding opportunities, which are separate and independent of WiML travel funding. More details can be found on the NeurIPS website . Travel funding application form [now CLOSED]: Authors that have submitted their work will receive the application form starting on September 2, 2022. The application deadline is September 8th, 2022. Applications received past this deadline will not be considered. * Important Note * More information on funding opportunities can be found in our FAQ section of our webpage. AREA CHAIRS Area chairs should be women or non-binary. The role of area chairs is to write a review and suggest an accept/reject decision for each abstract. We expect each area chair to be responsible for up to 10 one-page abstracts. Area chair application form [now CLOSED]: If you are interested in being an area chair, please apply via the application link . Update: the deadline for the AC application has now passed (deadline August 24th). Thank you for your interest. Visa invitation letter Information on visa invitation letter requests can be found in our FAQ section of our webpage. ORGANIZERS Sergul Aydore (Amazon AI) Gloria Namanya (Makerere AI Research) Mariam Arab (Microsoft and Simon Fraser University) Beliz Gunel (Google AI) Kimia Nadjahi (MIT) Konstantina Palla (Spotify Research) Questions? Check out the FAQs or reach us at workshop[at]wimlworkshop[dot]org PLATINUM SPONSORS GOLD SPONSORS SILVER SPONSORS BRONZE SPONSORS SUPPORTERS Committee ORGANIZERS Sergül Aydöre General Chair Konstantina Palla Senior Program Chair Gloria Namanya Finance and Sponsorship Chair Beliz Gunel Mentorship Chair Mariam Arab Logistics Chair Kimia Nadjahi Student Program and Funding Chair Code of Conduct The open exchange of ideas, the freedom of thought and expression, and respectful scientific debate are central to the goals of Women in Machine Learning, Inc. (“WiML”) activities; this requires a community and an environment that recognizes and respects the inherent worth of every person. The purpose of this Code of Conduct (CoC) is to outline expected standards of behavior during WiML activities. Scope This CoC applies to all WiML activities, including but not limited to: Events organized, hosted, co-branded, or in cooperation with WiML Submissions and reviewing processes run by WiML. Communications are sent through communication channels associated with WiML, including but not limited to social media. Meetings and discussions associated with WiML activities. If an activity is in cooperation with another organization, if the other organization has its own CoC, the union of both CoCs apply. Responsibility All attendees, speakers, mentors, panelists, area chairs, reviewers, sponsors, contractors, organizers, volunteers, members of the WiML Board of Directors and Senior Advisory Council (referred to as “Participants” collectively throughout this document) involved in WiML activities as described above are required to comply with this CoC. Reviews should actively avoid subtle discrimination, however inadvertent. In particular, reviewers should avoid comments in reviews about English style or grammar that may be interpreted as implying that the author is “foreign” or “non-native”. Sponsors are equally subject to this CoC. In particular, sponsors should not use images, activities, or other materials that reinforce gender stereotypes or are of a sexual, racial, or otherwise offensive nature at WiML events. Booth staff, including but not limited to volunteers, should not create a sexualized environment. Unacceptable Behavior WiML is dedicated to providing an experience for all participants that is free from harassment, bullying, discrimination, and retaliation. This includes offensive comments related to gender, gender identity and expression, age, sexual orientation, disability, physical appearance, body size, race, ethnicity, religion (or lack thereof), politics, technology choices, or any other personal characteristics or considerations made unlawful by federal, state, or local laws, ordinances, or regulations. Inappropriate or unprofessional behavior that interferes with another participant’s full participation will not be tolerated. This includes bullying, intimidation, personal attacks, harassment, sustained disruption of talks or other events, sexual harassment, stalking, following, harassing photography or recording, inappropriate physical contact, unwelcome sexual attention, public vulgar exchanges, derogatory name-calling, or diminutive characterizations, all of which are unwelcome in this community. Advocating for, or encouraging, any of the above behavior, is also considered harassment. No use of images, activities or other materials that are of a sexual, racial, or otherwise offensive nature that may create an inappropriate or toxic environment is permitted. Disorderly, boisterous, or disruptive conduct including but not limited to fighting, coercion, theft, damage to property, or any mistreatment or non-businesslike behavior towards other participants is not tolerated. Scientific misconduct—including but not limited to fabrication, falsification, or plagiarism of paper submissions or research presentations—is prohibited. Reporting If you have concerns related to your participation or interaction at a WiML activity, observe someone else’s difficulties, or have any other concerns you wish to share, you can make a report: Anytime: By email at wiml.code.of.conduct@gmail.com ‬ During an event: In-person to organizers, volunteers, or any member of the WiML Board of Directors. They will then direct you to the designated responder(s) for that event. Organizers and volunteers can be identified by special badges marked as “ORGANIZER” or “VOLUNTEER”. Members of the WiML Board of Directors can be identified by special badges marked as “WiML Board”. There is no deadline by which to make a report. If the person receiving your report is not the designated responder for that event, they will direct you to a designated responder and/or provide you immediate medical or security help and assist you to feel safe for the duration of the activity. Designated responders will follow WiML procedures to respond to and investigate your report. Enforcement Any participant asked by any member of the community to stop any unacceptable behavior is expected to comply immediately. A response of “just joking” will not be accepted; behavior can be harassing without an intent to offend. If a participant engages in behavior that violates this CoC, WiML retains the right to take any action deemed appropriate, including but not limited to: Formal or informal warnings Barring or limiting continued attendance and participation, including but not limited to expulsion from the event Barring from participating in or deriving benefits from future WiML activities Exclusion from WiML opportunities, e.g. leadership, organizing, volunteering, speaking, reviewing, sponsoring, etc. Reporting the incident to the offender’s local institution or funding agencies Reporting the incident to local law enforcement The same actions may be taken toward any individual who engages in retaliation or who knowingly makes a false allegation of harassment. If action is taken, an appeals process will be made available. Investigation Reports of violations will be handled at the discretion of the WiML Board of Directors, who will investigate reports and bring the issue to resolution. Reports made during the activity will be responded to within 24 hours; reports made at other times will be responded to in less than five weeks. All reports will be handled as confidentially as possible and information will be disclosed only as it is necessary to complete the investigation and bring to resolution. There may be situations (such as those involving Title IX issues in the United States and venue- or employer-specific policies) where the member of the WiML Board of Directors informed of the violation will be under an obligation to file a report with another individual or organization outside of WiML. Ongoing Review The WiML Board of Directors welcomes feedback from the community on this CoC policy and procedures; please contact us by email at info@wimlworkshop.org . Acknowledgments This CoC policy was written by adapting the wording and structure from other CoC policies and procedures by Geek Feminism Wiki (created by the Ada Initiative), NeurIPS , ACM , Montreal AI Symposium , and Deep Learning Indaba . FAQs Do you have a list of members? How can I join WiML? WiML doesn’t have “members” per se, any women working in machine learning can be part of the WiML network. We have a mailing list for anyone to post announcements of interest to the WiML network and an opt-in, necessarily incomplete directory of women working in machine learning . How can I join the WiML mailing list? Join the mailing list directly here . What kind of events do you organize? Our flagship event is the annual WiML Workshop, typically co-located with NeurIPS, a machine learning conference. We also organize an “un-workshop” at ICML, as well as small events (e.g. lunches and receptions) at other machine learning conferences, such as CoRL, COLT, etc. Check out our events page for up-to-date listings of events. Do you have local meetups? No, but check out WiMLDS (website, Twitter), another organization that supports women in machine learning by organizing local meetups. How do I reach the WiML network? Use our mailing list . How can I sponsor WiML? Thank you for your interest in sponsoring WiML! See this page for more information. I am looking for an invited speaker / panelist / area chair / program committee member etc. Can WiML help me? Use our directory of women in machine learning or post this opportunity to our mailing list . I want to circulate a job posting. Can WiML help me? Post directly to our mailing list . How can I support WiML? You can: Post interesting opportunities and job postings to our mailing list . Use our directory of women in machine learning to find invited speakers, panelists, area chairs, program committee members, etc, or post these opportunities to our mailing list . Sponsor us. See this page for more information. Volunteer at one of our events. Check out our events page for up-to-date listings of events. Apply to be an area chair or reviewer at WiML Workshop (see this year’s workshop website for info). Take pictures at our events and share with us (tag @wimlworkshop on Twitter). If you see us mentioned in the media, send us a link at info@wimlworkshop.org . And many others! How did WiML start? What's the founding story? Hanna Wallach, Jennifer Wortman Vaughan, Lisa Wainer, and Angela Yu shared a room at NIPS 2005. Late one night, they talked about how exciting it was that there were FOUR female students at NIPS that year. They tried to list all the women in machine learning they know of and got to 10, then started talking about creating a meeting or gathering for all these women and perhaps others that they didn’t know about. Jenn, Lisa, and Hanna put together a proposal for a session at the 2006 Grace Hopper Celebration of Women in Computing that would feature talks and posters by female researchers and students in machine learning. The 1st WiML workshop was co-located with the 2006 Grace Hopper Celeberation. In 2008, WiML Workshop moved to NIPS (renamed NeurIPS in 2018) and there has been a WiML Workshop at NeurIPS every year since. In 2020, WiML introduced an “un-workshop” at ICML based on the concept of an “un-conference”, a form of discussion on a pre-selected topic that is primarily driven by participants. Read more WiML history here ! What are the mentorship roundtables? Each table seats 8-10 people (including mentors), with two mentors leading the discussion on a particular topic at each table. WiML attendees rotate between tables every 15-20 minutes. This allows attendees to gain exposure to different topics, and mentors to meet a large number of WiML attendees. Is WiML an archival venue? No, WiML is a non-archival venue. This means that, if your contribution is accepted, we will not be asking you to submit a camera-ready version of it, nor will we publish it anywhere (neither online nor in proceedings of any sort). We will only make the title and authors’ names available in the program book. I have a question that isn't answered here. How do I reach you? We receive a lot of email. Help us help you by reaching out through the appropriate channels. Job posting, announcement, CFP, etc: Post directly to WiML mailing list . Have event pictures to share: post on Twitter and tag @wimlworkshop Workshop enquiries: workshop@wimlworkshop.org If you are a company interested in sponsoring WiML: sponsorship@wimlworkshop.org Any other enquiries: info@wimlworkshop.org If you email us, don’t cc multiple email addresses — this saves us time routing your email to one mailbox, and reduces the chances of your email getting lost. Thank you in advance! Back To Top

< Back Katherine M. Kinnaird, PhD WiML President (2016-2019), Director (2014-2015) Visit my Profile

All events 2nd WiML Mentoring Program for PhD Applications: Panel on Fellowship Applications Virtual September 22, 2022 9:00 m -10:00 am This event, part of the WiML’s 2022-2023 Mentorship Program on the theme of PhD applications, takes place 9-10am PT in Zoom. Mentors and mentees of the 2022-2023 Mentorship Program are invited to attend. Panelists: Luisa Cutillo (Leeds), Ioana Bica (University of Oxford; Alan Turing Institute), Amy Zhang (University of Washington), Aleksandra Korolova (Princeton University), Eric Wallace (University of California Berkeley) Moderator: Alessandra Tosi (Mind Foundry) Previous Next

All events WiML Workshop 2016 Barcelona, Spain December 5, 2016 08:00 am — 05:00 pm The 11th annual Women in Machine Learning workshop will be colocated with NIPS 2016 in Barcelona, Spain in December 2016. See the workshop website for details! The organizers are: Diana Cai, Deborah Hanus, Sarah Tan, Isabel Valera, and Rose Yu. The invited speakers are: Jennifer Chayes, Maya Gupta, Anima Anandkumar, and Suchi Saria, with Tamara Broderick and Sinead Williamson giving remarks on WiML updates. Recorded talks can be found at this link . Previous Next

All events WiML Luncheon @ ICML 2011 Bellevue, Washington June 30, 2011 12:00 pm — 01:40 pm WiML is hosting a luncheon at ICML 2011 in Bellevue, Washington. All women working on machine learning are invited. Date: Tuesday, June 30, 2011, 12pm-1.40pm Venue: Maple Room,Hyatt Regency Bellevue, Bellevue Event details: http://www.icml-2011.org/forms/Brochure_Final4.pdf If you see any errors or omissions or have any information to contribute to this page, please contact us at info@wimlworkshop.org Previous Next

Empowering Women in Machine Learning: Amplifying Achievements, Elevating Voices, Building Leaders, and Bridging Gaps to enhance the experience of women in machine learning. 2nd Women in Machine Learning Un-Workshop The 2nd WiML virtual Un-Workshop is co-located with virtual ICML on Wednesday July 21st, 2021. Speakers Logistics Program Call for Participation Committee FAQ Code Of Conduct Machine learning is one of the fastest growing areas of computer science research. Search engines, text mining, social media analytics, face recognition, DNA sequence analysis, speech and handwriting recognition, healthcare analytics are just some of the applications in which machine learning is routinely used. In spite of the wide reach of machine learning and the variety of theory and applications, it covers, the percentage of female researchers is lower than in many other areas of computer science. Most women working in machine learning rarely get the chance to interact with other female researchers, making it easy to feel isolated and hard to find role models. The annual Women in Machine Learning Workshop is the flagship event of Women in Machine Learning . This technical workshop gives female faculty, research scientists, and graduate students in the machine learning community an opportunity to meet, network and exchange ideas, participate in career-focused panel discussions with senior women in industry and academia and learn from each other. Underrepresented minorities and undergraduates interested in machine learning research are encouraged to attend. We welcome all genders; however, any formal presentations, i.e. talks and posters, are given by women. We strive to create an atmosphere in which participants feel comfortable to engage in technical and career-related conversations. The workshop started at the 2006 Grace Hopper Celebration and moved to NeurIPS in 2008. A History of WiML poster was created in 2015 to celebrate the 10th workshop. This is the 2nd WiML Un-Workshop and is co-located with ICML . This event along with ICML are virtual events due to COVID-19. The term “un-workshop” is based on the concept of an “un-conference”, a form of discussion on a pre-selected topic that is primarily driven by participants. The overall goal of the un-workshop is to advance research through collaboration and increased interaction among participants from diverse backgrounds. Different from the workshop, the un-workshop’s main focus is topical breakout sessions, with short invited talks and casual, informal poster presentations. Besides this un-workshop and annual workshop which is co-located with NeurIPS, Women in Machine Learning also organizes events such as lunch at AAAI conference, maintains a public directory of women active in ML, profiles the research of women in ML, and maintains a list of resources for women working in ML. Invited Speakers Celia Cintas Research Scientist, IBM Research - Nairobi Yingzhen Li Lecturer at Department of Computing. Imperial College London, UK Sarah Hooker Research Scientist at Google Brain Luciana Benotti Associate Professor at the Universidad National de Cordoba (UNC) Argentina Location This un-workshop takes place virtually due to COVID-19. Please check the program book for a complete overview of the program. Rocket.chat info desk and tech support If you have general questions or technical difficulties on the day of the event, drop by the Rocket.chat window on the workshop page on icml.cc . Best Practices for virtual events Virtual conferences can be tricky, and there are a lot of unintuitive ways to make your experience (and the experience of others) a little better. You can read some of our tips here . Information on Talks, Panel and Breakout Sessions We will be hosting the talks, panel as a Zoom webinar. We will also host breakout sessions on Zoom. You can join these sessions by clicking the links on the ICML Un-Workshop webpage . As an attendee, you will not be able to unmute yourself. If you have questions about the content of the talk, please submit the questions using the Zoom Q&A feature. Time permitting, and depending on the volume of questions, the moderator will either ask your question for you or confirm with you to ask the question yourself and unmute you at a suitable time. Note that Q&A will be moderated by us so you will only be able to see some of the questions of the other attendees. If you want to send messages to the moderators during the seminar, please use the Zoom chat feature. If you have not used Zoom before, we highly recommend downloading and installing the Zoom client before the meeting. Additional instructions on how to use Zoom during a webinar can be found here . Information on Poster Session and Mentorship Social The WIML Un-Workshop poster session, mentorship social and The Joint Affinity Groups Poster Session takes place in Gather.Town. You can join these sessions by clicking the links on the ICML Un-Workshop webpage . See Gather.Town guidelines to troubleshoot common access issues. If you face any issues, check these common video/audio issues or Gather.Town FAQ . An Important Note on ICML Registration Please note that the application form does not constitute registration for the WiML Un-Workshop. To attend the un-workshop, you need to register for ICML at https://icml.cc . There is no separate registration for the un-workshop. PROGRAM PANELISTS MENTORS ACCEPTED POSTERS The 2021 WiML Un-Workshop at ICML will be held virtually on Wednesday, July 21th, 2021. WiML will also participate in the ICML Affinity Groups Joint Poster Session with Queer in AI on Monday, July 19th. All participants are required to abide by the WiML Code of Conduct . Please use this link to access the Un-Workshop on ICML. Wednesday, July 21th, 2021 Time (ET/New York ) - Event 09:40 – 09:50: Introduction and Opening Remarks 09:50 – 10:00: WiML D&I Chairs Remarks 10:00 – 10:25: Invited talk – Yingzhen Li 10:25 – 11:30: Breakout sessions #1 11:30 – 12:00: Virtual Coffee Break and Poster Session #1 12:00 – 12:25: Invited Talk – Celia Cintas 12:25 – 13:30: Breakout Sessions #2 13:30 – 14:30: Sponsor Expo: Presentations by Microsoft, QuantumBlack, Apple, and Facebook 14:30 – 15:30: Mentoring Social 15:30 – 18:45: Break + Informal Social 18:45 – 19:25: Invited Talk – Sara Hooker 19:25 – 20:30: Breakout Sessions #3 20:30 – 21:00: Virtual Coffee Break and Poster Session #2 21:00 – 21:25: Invited Talk – Luciana Benotti 21:25 – 22:30: Breakout Sessions #4 22:30 – 23:30: Panel Discussion – Sarah Dean, Sarah Aerni, Sylvia Herbert, Kalesha Bullard, Amy Zhang (moderator) 23:30 – 23:45: Closing Remarks Our sponsor booths are open during the Un-Workshop. Please find information on their schedules and events here . For more details about the breakout sessions (e.g. affiliations), please use this link . You can submit your questions to the panelists through this link . Breakout session #1, 10:25 AM – 11:30 AM ET ID - Session title - Leaders - Facilitators 1.1 Catching Out-of-Context Misinformation with Self-supervised LearningShivangi AnejaMamatha Thota, Vishwali Mhasawade 1.2 School mapping using computer vision technologySafa SulimanMaryam Daniali 1.3 Data Integration and Predictive Modeling for Precision Medicine in OncologyMehreen Ali Esther Oduntan 1.4 Unsupervised Learning in Computer VisionAyca Takmaz, Clara Fernandez Labrador Naina Dhingra 1.5 Machine Learning for Privacy: An Information Theoretic PerspectiveEcenaz Erdemir, Fatemehsadat Mireshghallah Cemre Cadir 1.6 Fundamentals of Contrastive Learning in VisionSamrudhdhi Rangrej, Ibtihel Amara, Zahra Vaseqi Farzaneh Askari 1.7 Exploring probabilistic sparse inferencing through the triangulation of neuroscience, computing and philosophyGagana B, Stuti Gupta Akash Smaran 1.8 Neural Machine Translation for Low-Resource LanguagesEn-Shiun Annie Lee, Surangika Ranathunga, Rishemjit Kaur, Marjana Prifti SkenduliNiti M KC, Jivat Neet Kaur Breakout session #2, 12:25 PM – 1:30 PM ET ID - Session title - Leaders - Facilitators 2.1 Geometry and Machine LearningMelanie WeberAnkita Shukla 2.2 Leveraging Open-Source Tools for Natural Language ProcessingJennifer Glenskii RanaAneri Rana, Niti M KC 2.3 Challenges and Opportunities in ML for Health Care: How to address interpretability in clinical decision making?Annika Marie Schoene, En-Shiun Annie Lee, Peiyuan Zhou Malinda Vania 2.4 Leading the Way for the Next Generation of Black Women in STEMLouvere Walker-Hannon, Dr. Tracee Gilbert Mozhgan Saeidi 2.5 Un-bookclub Algorithms of OppressionRajasi Desai, Esther Oduntan, Anoush Najarian Sindhuja Parimalarangan 2.6 Research within community: how to cultivate a nurturing environment for your researchRosanne LiuMehreen Ali 2.7 Explainable machine learning: do we have the right tools?Michal Moshkovitz, Chhavi Yadav Shreya Ghosh 2.8 Decision-Making in Social Settings: Addressing Strategic Feedback EffectsMeena Jagadeesan, Celestine Mendler-Dünner Frances Ding Breakout session #3, 7:25 PM – 8:30 PM ET ID - Session title - Leaders - Facilitators 3.1 Does your model know what it doesn’t know? Uncertainty estimation and out-of-distribution (OOD) detection in deep learningJie Ren, Polina Kirichenko, Sharon Yixuan Li, Sergul Aydore, Haleh Akrami Liyan Chen 3.2 ML Applications in Big CodeSonia Kim, Mozhgan Saeidi Shima Shahfar 3.3 Connecting Novel Perspectives on GNNs: A Cross-Domain OverviewIlke Demir, Nesreen Ahmed, Vasuki Narasimha Swamy, Subarna Tripathi Ancy Tom 3.4 Bridging the gap between academia and industryChip Huyen, Sharon Zhou Sasha Luccioni 3.5 Variational Inference for Neural NetworksSahar Karimi, Audrey Flower Gargi Balasubramaniam 3.6 Responsible AI in production: Technical and Ethical considerationsParul Pandey, Himani Agrawal Wanda Wang Breakout session #4, 9:25 PM – 10:30 PM ET ID - Session title - Leaders - Facilitators 4.1 AI and Creativity: Approaches to Generative ArtAneta NeumannAncy Tom 4.2 Attrition of women and minoritized individuals in AIJeff Brown, Christine Custis, Madu Srikumar, Himani AgrawalJeff Brown, Christine Custis, Madu Srikumar 4.3 Safely navigating scalability-reliability trade-offs in ML methodsRuqi Zhang, A. Feder CooperMonica Munnangi Sponsor Expo Presentations, 1:30 PM – 2:30 PM ET Time (ET/New York ) - Sponsor - Speaker - Title 13:30 – 13:45 Microsoft Jennifer Neville Improving Productivity with Graph ML over Content-Interaction Networks 13:45 – 14:00 Quantum Black Viktoriia Oliinyk Algorithmic Fairness: Machine Learning with a Human Face 14:00 – 14:15 Apple Lizi Ottens Machine Learning at Apple 14:15 – 14:30 Facebook Ning Zhang Future of AI-Powered Shopping Mentorship Social, 2:30 PM – 3:30 PM ET ID - Mentor - Topic 1 Dina Obeid (Harvard) A non-linear career path in Machine Learning 2 Shakir Mohamed (DeepMind) Socio-Technical AI Research 3 Been Kim (Google Brain) Industry Research and Managing Up 4 Anna Goldenberg (U Toronto) Two body problem in academia, Raising a family, Grant strategies, Looking for a job to deploying ML in a hospital setting 5 Lalana Kagal (MIT) Maintaining work-life balance 6 Angelique Taylor (Cornell University) Transitioning from PhD to Assistant Professor Invited talk: Celia Cintas Towards fairness & robustness in machine learning for dermatology Abstract: Recent years have seen an overwhelming body of work on fairness and robustness in Machine Learning (ML) models. This is not unexpected, as it is an increasingly important concern as ML models are used to support decision-making in high-stakes applications such as mortgage lending, hiring, and diagnosis in healthcare. Currently, most ML models assume ideal conditions and rely on the assumption that test/clinical data comes from the same distribution of the training samples. However, this assumption is not satisfied in most real-world applications; in a clinical setting, we can find different hardware devices, diverse patient populations, or samples from unknown medical conditions. On the other hand, we need to assess potential disparities in outcomes that can be translated and deepen in our ML solutions. In this presentation, we will discuss how to evaluate skin-tone representation in ML solutions for dermatology and how we can enhance the existing models’ robustness by detecting out-out-distribution test samples (e.g., new clinical protocols or unknown disease types) over off-the-shelf ML models. Invited talk: Yingzhen Li Evaluating approximate inference for BNNs Abstract:Bayesian Neural Network is one of the major approaches for obtaining uncertainty estimates for deep learning models. Key to the success is the selection of the approximate inference algorithms used to compute the approximate posterior, with mean-field variational inference (MFVI) and MC-dropout being the most popular variants. But is the good downstream uncertainty estimation performance of BNNs attributed to good approximate inference? In this talk I will discuss some of our recent results towards answer this question. I will also discuss briefly the computational reasons of the preference of MFVI/MC-dropout and describe our latest work to make BNNs more memory efficient. Invited talk: Sara Hooker Characterizing the Generalization Trade-offs Incurred By Compression Abstract: To-date, a discussion around the relative merits of different compression methods has centered on the trade-off between level of compression and top-line metrics such as top-1 and top-5 accuracy. Along this dimension, compression techniques such as pruning and quantization are remarkably successful. It is possible to prune or heavily quantize with negligible decreases to test-set accuracy. However, top-line metrics obscure critical differences in generalization between compressed and non-compressed networks. In this talk, we will go beyond test-set accuracy and discuss some of my recent work measuring the trade-offs between compression, robustness and algorithmic bias. Characterizing these trade-offs provide insight into how capacity is used in deep neural networks — the majority of parameters are used to represent a small fraction of the training set. Formal auditing tools like Compression Identified Exemplars (CIE) also catalyze progress in training models that mitigate some of the trade-offs incurred by compression. Invited talk: Luciana Benotti Errors are a crucial part of dialogue Abstract: Collaborative grounding is a fundamental aspect of human-human dialogue which allows people to negotiate meaning; in this talk, I argue that current deep learning approaches to dialogue systems don’t deal with it adequately. Making errors, and being able to recover from them collaboratively, is a key ingredient in grounding meaning, but current dialogue systems can’t do this. I will illustrate the pitfalls of being unable to ground collaboratively, discuss what can be learned from the language acquisition and dialog systems literature, and reflect on how to move forward. I will urge the community to proceed by addressing a research gap: how clarification mechanisms can be learned from data. Novel research methodologies which highlight the importance of the role of clarification mechanisms are needed for this. I will present an annotation methodology, based on a theoretical analysis of clarification requests, which unifies a number of previous accounts. Dialogue clarification mechanisms are an understudied research problem and a key missing piece in the giant jigsaw puzzle of natural language understanding. I will conclude this talk with an open call for collaborators that share the vision presented. WiML Accepted Posters in Poster Session s (11:30 AM – 12:00 PM ET and 20:30 PM – 21:00 PM ET) and Joint Affinity Poster Session on Gather.Town (Monday 19 Jul 9:00 PM — 11:00 PM ET) Machine Learning Applications in Animal Sciences A mbreen Hamadani* (PhD Scholar, Animal Genetics and Breeding, SKUAST-K), Nazir A Ganai (Professor, Animal Genetics and Breeding, SKUAST-K) Emulating Aerosol Microphysics with Machine Learning Paula Harder* (University of Kaiserslautern) Duncan Watson-Parris (University of Oxford), Domink Strassel (Fraunhofer ITWM), Nicolas Gauger (University of Kaiserslautern), Philip Stier (University of Oxford), Janis Keuper (Offenburg University) Network Experiment Design for estimating Direct Treatment Effects Zahra Fatemi*(University of Illinois at Chicago), Elena Zheleva (Universty of llinois at Chicago) Adversarial Robust Model Compression using In-Train Pruning Manoj Rohit Vemparala (BMW Group), Nael Fasfous (Technical University of Munich), Alexander Frickenstein (BMW Group), Sreetama Sarkar* (BMW Group), Qi Zhao (Karlsruhe Institute of Technology), Sabine Kuhn (BMW Group), Lukas Frickenstein (BMW Group), Anmol Singh (BMW Group), Christian Unger (BMW), Naveen Shankar Nagaraja (BMW Group), Christian Wressnegger (Karlsruhe Institute of Technology), WALTER STECHELE (Technical University of Munich) Iterative symbolic regression for learning transport equations Mehrad Ansari*, Heta A. Gandhi*, David Foster, Andrew D. White; Department of Chemical Engineering, University of Rochester, Rochester, NY 14627 Cost Aware Asynchronous Multi-Agent Active Search Arundhati Banerjee*(School of Computer Science,Carnegie Mellon University), Ramina Ghods (School of Computer Science, Carnegie Mellon University), Jeff Schneider (School of Computer Science, Carnegie Mellon University) Exploration and preference satisfaction trade-off in reward-free learning Noor Sajid (WCHN, U CL), Panagiotis Tigas (OATML, Oxford University), Alexey Zakharov (Huawei, Imperial College), Zafeirios Fountas (Huawei, WCHN, UCL), Karl Friston (WCHN, UCL) HYBRIDNET: A NETWORK THAT LEVERAGES ON CLASSICAL AND NON-CLASSICAL COMPUTER VISION TECHNIQUES FOR FEW SHOT LEARNING ON INFRARED IMAGERY Maliha Arif * (PhD Candidate, Center for Research in Computer Vision – UCF) , Abhijit Mahalanobis ( Associate Professor, Center for Research in Computer Vision – UCF) Reinforcement Learning from Formal Specifications Kishor Jothimurugan (University of Pennsylvania), Suguman Bansal* (University of Pennsylvania), Obsert Bastani (University of Pennsylvania), Rajeev Alur (University of Pennsylvania) Clustering With Financial Fundamentals Jennifer Glenski* (Georgia Institute of Technology), Sara Srivastav (Georgia Institute of Technology), Rachel Riitano (Georgia Institute of Technology), Blake Heimann (Georgia Institute of Technology), Jenil Patel (Georgia Institute of Technology) Application of Knowledge Graph in Industry Samira Korani Contrastive Domain Adaptation Mamatha Thota(University of Lincoln), Georgios Leontidis(University of Aberdeen) Risk Analytics for Renewal of Purchase OrdersRisk Analytics for Renewal of Purchase Orders Shubhi Asthana (IBM Research), Pawan Chowdhary(IBM Research), Taiga Nakamura(IBM Research), Roberta Fadden (IBM) On the (Un-)Avoidability of Adversarial Examples Sadia Chowdhury* (York University), Ruth Urner (Assistant Professor, EECS Department, York University) Extraction of Adverse Drug Reactions from Tweets using Aspect Based Sentiment Analysis Sukannya Purkayastha (TCS Innovation Labs, Kolkata) Interpretation and transparency in acoustic emotion recognition Sneha Das* (Technical University of Denmark), Nicole Nadine Lønfeldt (Child and Adolescent Mental Health Center, Copenhagen University Hospital, Capital Region), Anne Katrine Pagsberg (Child and Adolescent Mental Health Center, Copenhagen University Hospital, Capital Region & Faculty of Health, Department of Clinical Medicine, Copenhagen University), Line H. Clemmensen (Technical University of Denmark) Seasonal forecasts of New Zealand’s local climate conditions with limited GCM inputs using Convolutional Neural Networks Fareeda Begum*(University of Canterbury), Varvara Vetrova (University of Canterbury), Nicolas Fauchereau (NIWA), Eibe Frank (University of Waikato), Tiger Xu(University of Waikato) Assessing the Carbon Intensity of Models Across Different Languages Gauri Gupta [1] (Manipal Institute of Technology), Krithika Ramesh* [1](Manipal Institute of Technology), Mirza Yusuf [1] (Manipal Institute of Technology), Praatibh Surana [1](Manipal Institute of Technology) (Equal contribution for all) A Low-rank Support Tensor Network Kirandeep Kour, Dr. Sergey Dolgov (University of Bath, UK), Prof. Dr. Martin Stoll (TU Chemnitz, Germany), Prof. Dr. Peter Benner (Max Planck Institute and TU Chemnitz, Germany) CricNet : Segment and Classify Cricket Events Sai Siddhartha Maram, Shambhavi Mishra*(Guru Gobind Singh Indraprastha University) Episodically optimized dynamical networks for robust motor control Sruti Mallik(*) (Electrical & Systems Engineering, Washington University in St Louis), ShiNung Ching (Electrical & Systems Engineering, Biomedical Engineering, Washington University in St. Louis) Open Set Detection via Similarity Learning Sepideh Esmaeilpour* (University of Illinois at Chicago), Lei Shu (Amazon AWS AI), Bing Liu(University of Illinois at Chicago) A modified limited memory Nesterov’s accelerated quasi-Newton *S. Indrapriyadarsini (Shizuoka University), Shahrzad Mahboubi (Shonan Institute of Technology), Hiroshi Ninomiya (Shonan Institute of Technology), Takeshi Kamio (Hiroshima University), Hideki Asai (Shizuoka University) Time-series Forecasting of Ionospheric Space Weather using Ensemble Machine Learning Randa Natras* (Technical University of Munich, Germany), Michael Schmidt (Technical University of Munich, Germany) SocialBERT : An Effective Few Shot Learning Framework Applied to a Social TV Setting Debarati Das* (Department of Computer Science, University of Minnesota Twin Cities), Roopana Chenchu (Department of Computer Science, University of Minnesota Twin Cities), Maral Abdollahi (Hubbard School of Journalism, University of Minnesota, Twin Cities), Jisu Huh (Hubbard School of Journalism, University of Minnesota, Twin Cities) and Jaideep Srivastava (Department of Computer Science, University of Minnesota Twin Cities) Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification Cristina Garbacea (University of Michigan Ann Arbor), Mengtian Guo (University of North Carolina at Chapel Hill), Samuel Carton (University of Colorado Boulder), Qiaozhu Mei (University of Michigan Ann Arbor) Alignment of Language Agents in V ideogames Gema Parreno ( Mempathy ) Using Weak Supervision to Identify Drug Mentions from Class Imbalanced Twitter Data Ramya Tekumalla* (Georgia State University), Juan M Banda (Georgia State University)) Call for Participation The 2nd WiML Un-Workshop is co-located with ICML on Wednesday, July 21st, 2021. The Women in Machine Learning will be organizing the second “un-workshop” at ICML 2021. This is an event format to encourage more participant interaction, especially with ICML going virtual this year. The un-workshop is based on the concept of an “un-conference”, a form of discussion on a pre-selected topic that is primarily driven by participants. Different from the workshop, the un-workshop’s main focus is topical breakout sessions, with short invited talks and casual, informal poster presentations. The overall goal of the un-workshop is to advance research through collaboration and increased interaction among participants from diverse backgrounds. Students, postdocs and researchers in all areas of Machine Learning who primarily identify as a woman and/or nonbinary are encouraged to submit one-page proposal to lead a breakout session on a certain research topic. While all presenters will identify primarily as a woman and/or nonbinary, all genders are invited to attend. Important dates June 14th, 2021 – Application form opens July 4th, 2021 – Deadline (anywhere on Earth) to apply for a breakout session, poster, registration fee funding, facilitating or volunteering July 10th, 2021 – Notification of acceptance of breakout session’s proposals July 10th, 2021 – Notification of acceptance of posters, registration fee funding, facilitators, volunteers July 21st, 2021 – WiML Un-Workshop Day Various ways of participating in WiML un-workshop Lead a breakout session: submit a proposal to lead a breakout session on a certain research topic. Facilitate a breakout session: assist breakout session leaders by taking notes and encouraging participant interactions and taking attendance. Present a poster: present a poster in a casual, informal setting. Volunteer: help with technical setup and in-event needs. Attend: participate in breakout session discussions. Breakout session proposals A breakout session is a 1-hour free-form discussion overseen by 1-3 leaders and with assistance from 1-2 facilitators to take notes and encourage participant interactions. We strongly encourage students, postdocs, and researchers who primarily identify as women and/or nonbinary in all areas of machine learning to submit a proposal to lead a topical breakout session. A complete proposal consists of a 1 page blind PDF (example here ) and the names and bios of leaders submitted separately in the application form. We strongly recommend having at least 2 leaders, with a diverse set of leaders preferred (see selection criteria below). The names of facilitators can also be provided if known at submission time. Otherwise, the organizers will match facilitators to breakout sessions. Breakout session leaders must identify primarily as women and/or nonbinary; facilitators can be of any gender. Only one proposal submission per leader is allowed. If there are multiple leaders, only one leader needs to submit the proposal. There are no proceedings. WiML registration fee funding is prioritized for accepted breakout session leaders who fulfill certain eligibility criteria (see details below) and do not have any other sources of funding. Breakout session guidelines: Role of leaders: Point-out key characteristics of your topic and make connections with other topics. Describe the key challenges in this research area on a high-level. Describe the key approaches on a high-level to provide intuition. Highlight possible points of discussion/goals to achieve during the session. Use graphics/imagery and materials e.g. slides as needed Encourage inclusive (rather than unilateral) discussions Role of facilitators: take notes and encourage participant interactions. Leaders and facilitators should anticipate a small additional time commitment before the un-workshop to receive briefing/training and a possible dry run. While the exact technology is still being determined, we anticipate using video-conferencing software (e.g. Zoom). Submission instructions for breakout sessions: Proposals must be no more than 1 page (including any references, tables, and figures) submitted as a PDF. Main body text must be minimum 11 point font size and page margins must be minimum 0.75 inches (all sides). Your proposal should stand alone, without linking to a longer paper or supplement. You should provide a brief description of the topics you’d like to discuss, any relevant references, a plan for how you’d organize the time (1 hour) allocated for a session, as well as some ideas on how you’d encourage discussion and participant interaction during the session. The PDF must not include identifying information, as it will be reviewed blind. In particular, the PDF should not contain information of the leaders or facilitators. Instead, submit their information in the application form. Selection criteria for breakout sessions: The degree to which it is expected that participants will find the topic interesting and valuable. Diversity of leaders and facilitators, including diversity of experience/seniority, affiliation, race, viewpoint and thinking regarding the topic, etc. Plans for encouraging discussion and participant interaction during the session. Facilitators If you are interested in facilitating a breakout session but have not yet connected with anyone submitting a breakout session proposal, you can indicate your interest in the application form. Organizers will match selected facilitators to breakout sessions. Facilitators should anticipate a small additional time commitment before the un-workshop to receive briefing/training and a possible dry run. Posters If you wish to present a poster, submit EITHER a short abstract (max 1500 characters) OR a PDF of the poster (only if you have it already). The poster may describe new, previously, concurrently published, or work-in-progress research. Posters in theory, methods, and applications are welcome. The poster presenter must identify primarily as a woman and/or nonbinary; other authors can be of any gender. The poster presenter does not need to be the first author of the work. Only one poster submission per presenter is allowed. Accepted posters will be presented in a casual, informal setting. This setting is very different from formal poster sessions, e.g. at WiML Workshop at NeurIPS. While the exact presentation format is still being determined, it may be as simple as a webpage with poster PDF and pre-recorded video. There are no oral or spotlight presentations. There are no proceedings. Submission instructions for posters: Submitted materials may contain identifying information, as posters for this un-workshop are not reviewed blind. Your submission should stand alone, without linking to a longer paper or supplement. You should convey motivation and give some technical details of the approach used. While we acknowledge that space is limited, some experimental results are likely to improve reviewers’ opinions of your poster. Registration fee funding The virtual nature of ICML and this un-workshop allows individuals from all over the world to attend. By funding a number of ICML registrations, WiML hopes to further expand the range of participants at this un-workshop. To apply for funding, you should: identify primarily as a woman and/or nonbinary; be a student, postdoc, or have an equivalent position (equivalent positions include unemployed recent grads and early career researchers from underrepresented geographical regions). Accepted breakout session leaders who fulfill the above eligibility criteria and do not have any other sources of funding will be prioritized for WiML funding. Other participants are also encouraged to apply. Priority will be given to individuals from underrepresented regions or groups, first-time attendees of ICML or similar conferences, and individuals who would benefit the most from this funding. Funding recipients must participate in at least one breakout session as a leader, facilitator, or attendee. Due to limited funding, we may not be able to support everyone eligible; however, we hope to support as many eligible applicants as possible. We also encourage you to apply for ICML volunteer and funding opportunities, which are separate and independent of WiML funding. Check the ICML website directly for details. Volunteering We are seeking volunteers to help with technical setup and virtual technology testing before the event, as well as help during the event, e.g. letting people into Zoom rooms, etc. We may also need emergency reviewers for breakout session proposals. You can indicate if you can help in any way in the application form here . Participation instructions To participate in ANY of the above roles and/or apply for registration fee funding, please fill in this application form by **July 4, 2021**. Selected breakout session leaders, facilitators, poster presenters, volunteers, and funding recipients will be notified individually by the dates mentioned above. If you only wish to attend, we still recommend you fill in this form to provide your timezone and topic preferences. All participants are required to abide by the WiML Code of Conduct . Important note: This form does not constitute registration for the WiML Un-Workshop. To attend the un-workshop, you need to register for ICML at https://icml.cc . Submission is now open! Organizers Beliz Gokkaya, Facebook Wenshuo Guo, University of California, Berkeley Arushi Majha, University of Cambridge Liyue Shen, Stanford Olivia Choudhury, Amazon Berivan Isik, Stanford Hadia Mohmmed Osman Ahmed Samil, Mila Vaidheeswaran Archana, Continental Automotive Questions? Check out the FAQs or reach us at workshop[at]wimlworkshop[dot]org PLATINUM SPONSORS Committee ORGANIZERS Beliz Gokkaya Software Engineer at Facebook, General Chair Wenshuo Guo PhD Student at University of California, Berkeley, Program Chair Hadia Mohmmed Osman Ahmed Samil Breakout Program and Logistics Co-Chair Berivan Isik PhD Student at Stanford University, Breakout Program and Logistics Co-Chair Olivia Choudhury Researcher at Amazon, Senior Program and Networking Chair Arushi Majha PhD Student at University of Cambridge, Finance and Sponsorship Chair Liyue Shen PhD Student at Stanford University, Funding and Volunteers Chair Vaidheeswaran Archana AI Engineer at Continental Automotive, Virtual Experience Chair Diversity and Inclusion Chair Danielle Belgrave, Principal Research Manager at Microsoft Research Supervolunteers We would like to acknowledge and warmly thank our super-volunteers who worked tirelessly to ensure a high quality un-workshop. Belen Saldias, MIT Elre Oldewage, University of Cambridge Mandana Samiei, McGill and Mila Niveditha Kalavakonda, University of Washington Seattle Weiwei Zong, Henry Ford Health System FAQs How do I register for the un-workshop? You need to register to ICML to attend to WiML and then please fill the application form provided. Please refer to call for participation for more details. Is filling the application form enough for register to WiML? No, you need to register to ICML . What is an un-workshop? The un-workshop is based on the concept of an “un-conference”, a form of discussion on a pre-selected topic that is primarily driven by participants. The overall goal of the un-workshop is to advance research through collaboration and increased interaction among participants from diverse backgrounds. How is an un-workshop different from WiML workshop at NeurlPS? WiML Workshop at NeurIPS is a one-day event with invited speakers, oral presentations, and posters. This year WiML is bringing a new event format to ICML to encourage more participant interaction, especially with ICML going virtual this year. Different from the workshop, the un-workshop’s main focus is topical breakout sessions, with short invited talks and casual, informal poster presentations. I'm a man. Can I attend WiML? Yes. All genders are welcome to attend! To do so, please register for ICML and fill the application form . Note, however, that all speakers, breakout session leaders and poster presenters will primarily identify as a woman and/or nonbinary, as our goal is to promote them and their work within the machine learning community. Where will the un-workshop take place? This is a virtual event. How much funding is available? Funding is distributed based on geographic location. Support varies from year to year and this year due to COVID-19, it will be a virtual event and ICML registration fee funding is available for participants who fulfill eligibility criteria. Is there a code of conduct? Yes. WiML requires all participants and reviewers to abide by our code of conduct . Is WiML an archival venue? No, WiML is a non-archival venue. This means that, if your contribution is accepted, we will not be asking you to submit a camera-ready version of it, nor will we publish it anywhere (neither online nor in proceedings of any sort). We will only make the title and authors’ names available in the program book. How can I get more information on un-workshop logistics? Please check out the logistics page! I want to support WiML by providing sponsorship / recruiting at the un-workshop. Who should I talk to? Thank you for your support! Please contact us . How can I join the WiML network? Join our Google Group . When and where do I submit my proposal? You can find more information on call for participation. Submission to the 2021 WiML un-workshop is now closed. How many breakout sessions will be on the day of the un-workshop? There are 4-time slots for 1-hour breakout sessions (marked as Breakout Sessions #1 to #4). Each of these 4-time slots will have several parallel breakout sessions. Why do breakout sessions involve Zoom and Slack? Zoom rooms are mainly for the breakout sessions for the specific one hour period. However, leaders can use Slack a few days before and after to ask participants to read some papers, ask them specific questions and keep the discussions going. Also, participants can ask questions regarding the breakout session’s topic in the Slack channel before the actual session. Can I make breakout rooms in the breakout session as a leader? Yes, leaders can make smaller breakout rooms to engage participants in smaller group discussions. How many attendees will be in each breakout session? We can’t promise the exact number but we are hoping for smaller groups (max 20) to increase interaction between participants. What is the whiteboard in Zoom rooms? Whiteboard is like a digital board and leaders and participants can write on it and explain a specific topic. More instructions are available here. Will we as leaders be given a chance to advertise our proposal topic before the un-workshop? Sure, you can advertise your session’s topic on Twitter for example and tag us on @WiMLworkshop and we can retweet that. Also, attendees will have access to the breakout session topics at least a week before the un-workshop. Can anyone who did not fill the WiML form still join the un-workshop? Anyone who is registered to ICML can join the un-workshop. I am new to the Gather.town platform being used for the live poster session. How can I prepare for it? Check out these guidelines. I have a question that's not answered here. How do I reach you? Contact us . Back To Top

< Back Amy Zhang, PhD WiML Director (2020-2022) Visit my Profile

< Back Alicia Yi-Ting Tsai, PhD WiML Secretary (2020-2023)

< Back Ilene Cartright WiML Director (2019-2022) Visit my Profile

17th Women in Machine Learning Workshop (WiML 2022) 17th Women in Machine Learning Workshop (WiML 2022) The Workshop is co-located with NeurIPS on Monday, November 28th, 2022 at the New Orleans Convention Center in Louisiana, USA. Speakers Logistics Program Call for Participation Committee FAQ Machine learning is one of the fastest growing areas of computer science research. Search engines, text mining, social media analytics, face recognition, DNA sequence analysis, speech and handwriting recognition, healthcare analytics are just some of the applications in which machine learning is routinely used. In spite of the wide reach of machine learning and the variety of theory and applications, it covers, the percentage of female researchers is lower than in many other areas of computer science. Most women working in machine learning rarely get the chance to interact with other female researchers, making it easy to feel isolated and hard to find role models. The annual Women in Machine Learning Un-Workshop is the flagship event in un-conference style of Women in Machine Learning , primarily intended to foster active participant engagement in the program. This technical workshop gives female faculty, research scientists, and graduate students in the machine learning community an opportunity to meet, network and exchange ideas, participate in career-focused panel discussions with senior women in industry and academia and learn from each other. Underrepresented minorities and undergraduates interested in machine learning research are encouraged to attend. We welcome all genders; however, any formal presentations, i.e. talks and posters, are given by women. We strive to create an atmosphere in which participants feel comfortable to engage in technical and career-related conversations. Now in its 4th year, the 2023 un-workshop is co-located with IC ML . Besides this annual un-workshop, Women in Machine Learning also organizes annual workshop at NeurIPS, events such as lunch or social at the AISTATS or AAAI conferences, maintains a public directory of women active in ML, profiles the research of women in ML, and maintains a list of resources for women working in ML. All participants are required to abide by the WiML Code of Conduct . I'm a paragraph. Click here to add your own text and edit me. It's easy. Invited Speakers Location Type of registration required to attend PROGRAM PANELISTS BREAKOUT SESSIONS COFFEE MEET & MINGLE SOCIAL Program Monday, November 28, 2022 [ in-person ] ( Time in CT) Morning Session 7:30 am - 8:30 am Registration & Breakfast 8:30 am - 8:45 am Opening Remarks - Konstantina Palla (Senior Program Chair) 8:45 am - 9:00 am D&I Chair remarks - Danielle Belgrave 9:00 am - 9:10 am Contributed talk ( Tejaswi Kasarla ) - "Maximum Class Separation as Inductive Bias in One Matrix" 9:10 am - 9:20 am Contributed talk ( Taiwo Kolajo ) - "Pre-processing of Social Media Feeds based on Integrated Local Knowledge Base" 9:20 am - 9:55 am Invited talk - Alice Oh - " The importance of multiple languages and multiple cultures in NLP research " 9:55 am - 10:10 am Coffee break 10:10 am - 10:25 am WiML Board Remarks - Jessica Schrouff 10:25 am - 11:00 am Invited talk - Raesetje Sefala - " Constructing visual datasets to answer research questions " 11:00 am - 11:10 am Contributed talk ( Pascale Gourdeau ) - "When are Local Queries Useful for Robust Learning?" 11:10 am - 11:20 am Contributed talk ( Annie S Chen ) - "You Only Live Once: Single-Life Reinforcement Learning" 11:20 am - 1:20 pm Mentorship roundtables & Lunch - Mentors: Adam Roberts, Stephanie Hyland, Bianca Zadrozny, Sima Behpour, Mercy Asiedu, Franziska Boenisch, Eleni Triantafillou, Isabela Albuquerque, Yisong Yue, Amy Zhang, Zelda Mariet, Tristan Naumann, Danielle Belgrave, Shakir Mohamed, Tong Sun, Gintare Karolina Dziugaite, Samy Bengio, Rianne van den Berg, Maja Rudolph, Luisa Cutillo, Ioana Bica, Clara Hu, Rosanne Liu, Jennifer Wei, Alice Oh, SueYeon Chung, Erin Grant, Sasha Luccioni, Michela Paganini, Mounia Lalmas-Roelke, Claire Vernade, Alekh Agarwal, Neema Mduma, Vinod Prabhakaran, Savannah Thais, Jonathan Frankle, Ce Zhang, Rose Yu, Jessica Schrouff, Bo Li, Katherine Heller, Ben Poole, Setareh Ariafar, Christina Pavlopoulou, Isabel Morlidge, Kavya Srinet, Cheng Zhang, Elise van der Pol, Diana Montanes, Lise Diagne, Le Yu, Megan Forrester. Afternoon Session 1:20 pm - 1:55 pm Invited talk - Bianca Zadrozny - " Machine Learning for Climate Risk " 1:55 pm - 2:05 pm Contributed talk ( Elizabeth Bondi-Kelly ) - "Human-AI Interaction in Selective Prediction Systems" 2:05 pm - 2:15 pm Contributed talk ( Gowthami Somepalli ) - "Investigating Reproducibility from the Decision Boundary Perspective." 2:15 pm - 2:35 pm Coffee break 2:35 pm - 3:10 pm Invited talk - Hima Lakkaraju - " A Brief History of Explainable AI: From Simple Rules to Large Pretrained Models " 3:10 pm - 4:10 pm Panel discussion 4:10 pm - 4:20 pm Closing Remarks 4:20 pm - 4:30 pm Poster setup 4:30 pm - 6:00 pm Joint Affinity Groups Poster Session Mentorship Roundtables AI and Creativity: Adam Roberts (Google Brain) Choosing between Academia and Industry: Stephanie Hyland (Microsoft Research) and Bianca Zadrozny (IBM Research) Continual Learning & Open-World Learning: Sima Behpour (Bosch) Founding and Funding Startups: Mercy Asiedu (Google) Gender-related challenges: Franziska Boenisch (Vector Institute) Generalization & Robustness: Eleni Triantafillou (Google Brain) and Isabela Albuquerque (DeepMind) Getting a job (academia): Yisong Yue (Caltech) and Amy Zhang (UT Austin) Getting a job (industry): Zelda Mariet (Google) Healthcare/clinical applications: Danielle Belgrave (DeepMind) and Tristan Naumann (Microsoft Research) Leadership: Shakir Mohamed (DeepMind) and Tong Sun (Adobe) Learning theory: Karolina Dziguaite (Google Brain) Life in industry research: Samy Bengio (Apple) and Rianne van den Berg (Microsoft Research) Life with kids: Maja Rudolph (BCAI) and Luisa Cutillo (University of Leeds) Mental health & surviving in grad school: Ioana Bica (DeepMind), Clara Hu (Google Brain), and Rosanne Liu (Google Brain) ML for Science: Jennifer Wei (Google) Natural language processing: Alice Oh (KAIST) Negotations in ML: Nicole Bannon (81cents) Neuroscience & cognitive science: Erin Grant (UCL), SueYeon Chung (NYU/Flatiron Institute), and Noga Zaslavsky Non-traditional paths in machine learning: Sasha Luccioni (HuggingFace) and Michela Paganini (DeepMind) Recommender systems: Mounia Lalmas-Roelke (Spotify) Reinforcement learning: Claire Vernade (DeepMind), Alekh Agarwal (Google), and Elise van der Pol (Microsoft Research) Seeking funding in academia: Neema Mduma (The Nelson Mandela African Institution of Science and Technology) Social science applications: Vinod Prabhakaran (Google Research), Savannah Thais (Columbia University), and Sarah Brown (University of Rhode Island) Systems and machine learning: Jonathan Frankle (Harvard University/MosaicML) and Ce Zhang (ETH Zurich) Time Series: Rose Yu (UCSD) Trustworthy machine learning: Jessica Schrouff (DeepMind), Bo Li (UIUC), and Katherine Heller (Google Research) Monday, December 5, 2022 [virtual](Time in ET) 9:30 am - 9:40 am Opening Remarks 9:40 am - 9:55 am Contributed talk ( Okechinyere J Achilonu ) - "Natural language processing for automated information extraction of cancer parameters from free-text pathology reports" 9:55 am - 10:10 am Contributed talk ( Paula Harder ) - "Physics-Constrained Deep Learning for Climate Downscaling" 10:10 am - 10:25 am Contributed talk ( Silvia Tulli ) - "Explanation-Guided Learning for Human-AI collaboration" 10:25 am - 10:40 am Contributed talk ( Mina Ghadimi Atigh ) - "Hyperbolic Image Segmentation" 10:40 am - 10:50 am Set up (for mentorship session) 10:50 am - 11:50 am Mentorship Panel (Discussion + Q&A) withJenn Wortman Vaughan (Microsoft Research),Colin Raffel (University of North Carolina)Kristen Grauman (University of Texas at Austin) 11:50 am - 12:00 pm Break 12:00 pm - 12:35 pm Sponsor Talks 2:00 pm - 4:00 pm Joint Affinity Groups Poster Session Call for Participation PLATINUM SPONSORS PLATINUM SPONSORS PLATINUM SPONSORS Committee ORGANIZERS WiML RECEPTION ORGANIZER ADVISORY SUPER VOLUNTEERS FAQs

< Back Svitlana Volkova, PhD WiML Director (2016-2018) Visit my Profile

< Back Pallika Kanani, PhD WiML Director (2013-2015)