NeurIPS 2020 : Les chercheurs de Mila se préparent en grand nombre

13 octobre 2020

La conférence sur les systèmes de traitement de l'information neuronale (NeurIPS) a dévoilé la liste complète des publications acceptées en prévision de sa 34e édition qui sera entièrement virtuelle.

Les titulaires des chaires NeurIPS 2020 ont annoncé que sur les 12 115 publications soumises, 1 903 au total ont été acceptées pour la conférence de cette année. Ce nombre très élevé est une illustration que la culture de la recherche devient de plus en plus compétitive.

Au vu de la pression croissante à laquelle nos chercheurs sont confrontés, il est important de commémorer tout le travail que nos étudiants et professeurs ont accompli en produisant leurs recherches et en organisant des ateliers pour la conférence.

Les publications acceptées de notre communauté couvrent un éventail de sujets, y compris, mais sans s'y limiter, de nouvelles approches de méta-apprentissage continu agnostique par modèle, des solutions à l'oversmoothness dans les réseaux convolutionnels de graphes, et deux méthodes de régularisation des politiques dans l'apprentissage de renforcement profond multi-agents.

Voici la liste complète des publications acceptées, ainsi qu’un aperçu des ateliers co-organisés par des membres de Mila (en anglais) :

          1. Untangling tradeoffs between recurrence and self-attention in neural networks

            2. Giancarlo Kerg, Bhargav Kanuparthi, Anirudh Goyal, Kyle Goyette, Yoshua Bengio, Guillaume Lajoie

            https://arxiv.org/abs/2006.09471

          2. Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples

            3. Samarth Sinha, Zhengli Zhao, Anirudh Goyal, Colin Raffel, Augustus Odena

            https://arxiv.org/abs/2002.06224

          3. Hybrid Models for Learning to Branch

            4. Prateek Gupta, Maxime Gasse, Elias B. Khalil, M. Pawan Kumar, Andrea Lodi, Yoshua Bengio

            https://arxiv.org/abs/2006.15212

          4. The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

            5. Harm van Seijen, Hadi Nekoei, Evan Racah, Sarath Chandar

            https://arxiv.org/abs/2007.03158

          5. Your GAN is Secretly an Energy-based Model and You Should use Discriminator Latent Sampling

            6. Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein, Hugo Larochelle, Liam Paull, Yuan Cao, Yoshua Bengio

            https://arxiv.org/abs/2003.06060

          6. Counterexample-Guided Learning of Monotonic Neural Networks

            7. Aishwarya Sivaraman, Golnoosh Farnadi, Todd Millstein, Guy Van den Broeck

            https://arxiv.org/abs/2006.08852

          7. Adversarial Example Games

            8. Joey Bose, Gauthier Gidel, Hugo Berard, Andre Cianflone, Pascal Vincent, Simon Lacoste-Julien, William Hamilton

            https://arxiv.org/abs/2007.00720

          8. Online Fast Adaptation and Knowledge Accumulation: A New Approach to Continual Learning

            9. Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam Laradji, Irina Rish, Alexandre Lacoste, David Vazquez, Laurent Charlin

            https://arxiv.org/abs/2003.05856

          9. Learning Dynamic Belief Graphs to Generalize on Text-Based Games

            10. Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikulás Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William Hamilton

            https://arxiv.org/abs/2002.09127

          10. Measuring Systematic Generalization in Neural Proof Generation with Transformers

            11. Nicolas Gontier, Koustuv Sinha, Siva Reddy, Christopher Pal

            https://arxiv.org/abs/2009.14786

          11. Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework

            12. Dinghuai Zhang, Mao Ye, Chengyue Gong, Zhanxing Zhu, Qiang Liu

            https://arxiv.org/abs/2002.09169

          12. Forethought and Hindsight in Credit Assignment

            13. Veronica Chelu, Doina Precup, Hado van Hasselt

          13. Real World Games Look like Spinning Tops

            14. Wojciech Marian Czarnecki, Gauthier Gidel, Brendan Tracy, Karl Tuyls, Shayegan Omidshafiefi, David Balduzzi, Max Jaderberg

            https://arxiv.org/abs/2004.09468

          14. Neumann Networks: Differential programming for supervised learning with missing values

            15. Marine Le Morvan, Julie Josse, Thomas Moreau, Erwan Scornet, Gaël Varoquaux

            https://arxiv.org/abs/2007.01627

          15. Training Linear Finite-State Machines

            16. Arash Ardakani, Amir Ardakani, Warren Gross

          16. RL Unplugged: Benchmarks for Offline Reinforcement Learning

            17. Caglar Gulcehre, Ziyu Wang, Alexander Novikov, Tom Le Paine, Sergio Gomez Colmenarejo, Konrad Zolna, Rishabh Agarwal, Josh Merel, Daniel Mankowitz, Cosmin Paduraru, Gabriel Dulac-Arnold, Jerry Li, Mohammad Norouzi, Matt Hoffman, Ofir Nachum, George Tucker, Nicolas Heess, Nando de Freitas

            https://arxiv.org/abs/2006.13888

          17. Graph Policy Network for Transferable Active Learning on Graphs

            18. Shengding Hu, Zheng Xiong, Xingdi Yuan, Marc-Alexandre Côté, Zhiyuan Liu, Jian Tang

            https://arxiv.org/abs/2006.13463

          18. Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

            19. Wangchunshu Zhou, Jinyi Hu, Hanlin Zhang, Xiaodan Liang, Maosong Sun, Chenyan Xiong, Jian Tang

          19. Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning

            20. Julien Roy, Paul Barde, Félix Harvey, Derek Nowrouzezahrai, Christopher Pal

            https://arxiv.org/abs/1908.02269

          20. Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks

            21. Yimeng Min, Frederik Wenkel, Guy Wolf

            https://arxiv.org/abs/2003.08414

          21. In search of robust measures of generalization

            22. Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel Roy

          22. An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay

            23. Scott Fujimoto, David Meger, Doina Precup

          23. Learning Graph Structure with A Finite-State Automaton Layer

            24. Daniel D. Johnson, Hugo Larochelle, Daniel Tarlow

            https://arxiv.org/abs/2007.04929

          24. Unsupervised Learning of Dense Visual Representations

            25. Pedro O. Pinheiro, Amjad Almahairi, Ryan Benmalek, Florian Golemo, Aaron Courville

          25. Equivariant Networks for Hierarchical Structures

            26. Renhao Wang, Marjan Albooyeh, Siamak Ravanbakhsh

          26. Symbols: Probing Learning Algorithms with Synthetic Datasets

            27. Alexandre Lacoste, Pau Rodríguez, Frederic Branchaud-Charron, Massimo Caccia, Issam Hadj Laradji, Alexandre Drouin, Matthew Craddock, Laurent Charlin, David Vázquez

            https://arxiv.org/abs/2009.06415

          27. Explicit Regularization is Stronger than Implicit Bias: A Study of SGD around Bad Global Minima

            28. Shengchao Liu, Dimitris Papailiopoulos, Dimitris Achlioptas

          28. Novelty Search in representational space for sample efficient exploration

            29. Ruo Yu Tao, Vincent François-Lavet, Joelle Pineau

            https://arxiv.org/abs/2009.13579

          29. La-MAML: Look-ahead Meta Learning for Continual Learning

            30. Gunshi Gupta, Karmesh Yadav, Liam Paull

            https://arxiv.org/abs/2007.13904

          30. Adversarial Soft Advantage Fitting: Imitation Learning Without Policy Optimization

            31. Paul Barde, Julien Roy, Wonseok Jeon, Joelle Pineau, Christopher Pal, Derek Nowrouzezahrai

            https://arxiv.org/abs/2006.13258

          31. Differentiable Causal Discovery from Interventional Data

            32. Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste, Simon Lacoste-Julien, Alexandre Drouin

            https://arxiv.org/abs/2007.01754

          32. Reward Propagation using Graph Convolutional Networks

            33. Martin Klissarov and Doina Precup

            https://arxiv.org/abs/2010.02474

          33. Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence

            34. Bastian Rieck, Tristan Yates, Christian Bock, Karsten Borgwardt, Guy Wolf, Nicholas Turk-Browne, Smita Krishnaswamy

            https://arxiv.org/abs/2006.07882

      Ateliers :

          1. Tackling Climate Change with Machine Learning

            2. Tegan Maharaj, Priya Donti, Lynn Kaack, Alexandre Lacoste, Andrew Ng, John Platt, Jennifer Chayes, Yoshua Bengio

            https://www.climatechange.ai/events/neurips2019.html

          2. Topological Data Analysis and Beyond

            3. Bastian Rieck, Frederic Chazal, Smita Krishnaswamy, Roland Kwitt, Karthikeyan Natesan Ramamurthy, Yuhei Umeda, and Guy Wolf

            https://tda-in-ml.github.io/

          3. Differential Geometry meets Deep Learning (DiffGeo4DL)

            4. Joey Bose, William Hamilton

            https://sites.google.com/view/diffgeo4dl/

          4. Differentiable vision, graphics, and physics applied to machine learning

            5. Krishna Murthy, Kelsey Allen, Victoria Dean, Johanna Hansen, Shuran Song, Florian Shkurti, Liam Paull, Derek Nowrouzezahrai, Josh Tenenbaum

            https://montrealrobotics.ca/diffcvgp/

          5. Resistance AI

            6. Mattie Tesfaldet, J Khadijah Abdurahman, William Agnew, Abeba Birhane, Elliot Creager, Agata Foryciarz, Pratyusha Ria Kalluri, Sayash Kapoor, Raphael Gontijo Lopes, Manuel Sabin, Marie-Therese Png, Maria Skoularidou, Ramon Vilarino, Rose E. Wang

            https://sites.google.com/view/resistance-ai-neurips-20/home

          6. Biological and Artificial Reinforcement Learning

            7. Raymond Chua, Feryal Behbahani, Sara Zannone, Doina Precup, Ida Momennejad, Blake Richards, Rui Ponte Costa

            https://sites.google.com/view/biologicalandartificialrl

          7. ML Retrospectives, Surveys & Meta-Analyses

            8. Chhavi Yadav, Prabhu Pradhan, Abhishek Gupta, Peter Henderson, Ryan Lowe, Jessica Forde, Jesse Dodge, Mayoore Jaiswal, Joelle Pineau

            https://ml-retrospectives.github.io/neurips2020/

          8. Object Representations for Learning and Reasoning

            9. William Agnew, Rim Assouel, Michael Chang, Antonia Creswell, Eliza Kosoy, Aravind Rajeswaran, Sjoerd van Steenkiste

            https://orlrworkshop.github.io/index.html

          9. Algorithmic Fairness through the Lens of Causality and Interpretability

            10. Golnoosh Farnadi, Awa Dieng, Jessica Schrouff, Matt Kusner, Fernando Diaz

            https://www.afciworkshop.org/

          10. AI for Earth Sciences

            11. Natasha Dudek, S. Karthik Mukkavilli, Johanna Hansen, Kelly Kochanski, S. Karthik Mukkavilli, Tom Beucler, Karthik Kashinath, Mayur Mudigonda, Amy McGovern

            https://ai4earthscience.github.io/neurips-2020-workshop/organizers.html 

          11. ML4H: Machine Learning for Health

            12. Benjamin Akera, Emily Alsentzer, Oliver J. Bear, Ioana Bica, Irene Chen, Fabian Falck, Stephanie Hyland, Dani Kyasseh, Matthew McDermott, Ehi Nosakhare, Charles Onu, Stephen Pfohl, Aahlad Manas Puli, Suproteem Sarkar, Allen Schmaltz

            https://ml4health.github.io/2020/pages/organizers.html

          12. Women in Machine Learning

            13. Amy Zhang, Elizabeth Wood, Mel Woghiren, Kristy Choi, Raquel Aoki, Judy Hanwen Shen, Belén Saldías, Xenia Miscouridou, Krystal Maughan, Xinyi Chen, Erin Grant

            https://wimlworkshop.org/neurips2020/contact-us/

          13. Offline Reinforcement Learning

            14. Rishabh Agarwal, Aviral Kumar, George Tucker, Doina Precup, Lihong Li

            https://offline-rl-neurips.github.io/