• wiml
  • October 28, 2016

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.


The program will include the following line-up of invited speakers:

The program will include the following mentors:

The program will include the following panelists:

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 Learning Shivangi Aneja Mamatha Thota, Vishwali Mhasawade
1.2 School mapping using computer vision technology Safa Suliman Maryam Daniali
1.3 Data Integration and Predictive Modeling for Precision Medicine in Oncology Mehreen Ali
Esther Oduntan
1.4 Unsupervised Learning in Computer Vision Ayca Takmaz, Clara Fernandez Labrador
Naina Dhingra
1.5 Machine Learning for Privacy: An Information Theoretic Perspective Ecenaz Erdemir, Fatemehsadat Mireshghallah
Cemre Cadir
1.6 Fundamentals of Contrastive Learning in Vision Samrudhdhi Rangrej, Ibtihel Amara, Zahra Vaseqi
Farzaneh Askari
1.7 Exploring probabilistic sparse inferencing through the triangulation of neuroscience, computing and philosophy Gagana B, Stuti Gupta


Akash Smaran
1.8 Neural Machine Translation for Low-Resource Languages En-Shiun Annie Lee, Surangika Ranathunga, Rishemjit Kaur, Marjana Prifti Skenduli Niti 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 Learning Melanie Weber Ankita Shukla
2.2 Leveraging Open-Source Tools for Natural Language Processing Jennifer Glenskii Rana Aneri 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 STEM Louvere Walker-Hannon, Dr. Tracee Gilbert
Mozhgan Saeidi
2.5 Un-bookclub Algorithms of Oppression Rajasi Desai, Esther Oduntan, Anoush Najarian
Sindhuja Parimalarangan
2.6 Research within community: how to cultivate a nurturing environment for your research Rosanne Liu Mehreen 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 Effects Meena 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 learning Jie Ren, Polina Kirichenko, Sharon Yixuan Li, Sergul Aydore, Haleh Akrami
Liyan Chen
3.2 ML Applications in Big Code Sonia Kim, Mozhgan Saeidi
Shima Shahfar
3.3 Connecting Novel Perspectives on GNNs: A Cross-Domain Overview Ilke Demir, Nesreen Ahmed, Vasuki Narasimha Swamy, Subarna Tripathi
Ancy Tom
3.4 Bridging the gap between academia and industry Chip Huyen, Sharon Zhou
Sasha Luccioni
3.5 Variational Inference for Neural Networks Sahar Karimi, Audrey Flower
Gargi Balasubramaniam
3.6 Responsible AI in production: Technical and Ethical considerations Parul 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 Art Aneta Neumann Ancy Tom
4.2 Attrition of women and minoritized individuals in AI Jeff Brown, Christine Custis, Madu Srikumar, Himani Agrawal Jeff Brown, Christine Custis, Madu Srikumar
4.3 Safely navigating scalability-reliability trade-offs in ML methods Ruqi Zhang, A. Feder Cooper Monica 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 QuantumBlack 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 Sessions (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)

Title Authors
Machine Learning Applications in Animal Sciences Ambreen 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, UCL), 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 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 Videogames 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))

Copyright © Women in Machine Learning 2020