ICLR

Linking Emergent and Natural Languages via Corpus Transfer

Shunyu Yao, Mo Yu, Yang Zhang, Karthik R Narasimhan, Joshua B. Tenenbaum, Chuang Gan

Comments ICLR 2022 Spotlight. Github repo: https://github.com/ysymyth/ec-nl

Safe Neurosymbolic Learning with Differentiable Symbolic Execution

Chenxi Yang, Swarat Chaudhuri

Comments Accepted as a poster at ICLR 2022

Score-Based Generative Modeling with Critically-Damped Langevin Diffusion

Tim Dockhorn, Arash Vahdat, Karsten Kreis

Comments ICLR 2022 (Spotlight)

Knowledge Removal in Sampling-based Bayesian Inference

Shaopeng Fu, Fengxiang He, Dacheng Tao

Comments In International Conference on Learning Representations, 2022

Evaluating Distributional Distortion in Neural Language Modeling

Benjamin LeBrun, Alessandro Sordoni, Timothy J. O'Donnell

Journal ref International Conference on Learning Representations. 2022

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Natalie Dullerud, Karsten Roth, Kimia Hamidieh, Nicolas Papernot, Marzyeh Ghassemi

Comments Published as a conference paper at ICLR 2022

Possibility Before Utility: Learning And Using Hierarchical Affordances

Robby Costales, Shariq Iqbal, Fei Sha

Comments ICLR 2022 camera-ready

Vision-Based Manipulators Need to Also See from Their Hands

Kyle Hsu, Moo Jin Kim, Rafael Rafailov, Jiajun Wu, Chelsea Finn

Comments First two authors contributed equally. ICLR 2022 (oral) camera-ready. 30 pages, 20 figures. Project website: https://sites.google.com/view/seeing-from-hands

Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum

Kirby Banman, Liam Peet-Pare, Nidhi Hegde, Alona Fyshe, Martha White

Comments In International Conference on Learning Representations. 2021

Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond

Chulhee Yun, Shashank Rajput, Suvrit Sra

Comments ICLR 2022 camera-ready (selected for an oral presentation); 76 pages, 3 figures

FastSHAP: Real-Time Shapley Value Estimation

Neil Jethani, Mukund Sudarshan, Ian Covert, Su-In Lee, Rajesh Ranganath

Comments ICLR 2022 Camera Ready, 20 pages, 10 figures, 3 tables

Online Adversarial Attacks

Andjela Mladenovic, Avishek Joey Bose, Hugo Berard, William L. Hamilton, Simon Lacoste-Julien, Pascal Vincent, Gauthier Gidel

Comments ICLR 2022

Coordination Among Neural Modules Through a Shared Global Workspace

Anirudh Goyal, Aniket Didolkar, Alex Lamb, Kartikeya Badola, Nan Rosemary Ke, Nasim Rahaman, Jonathan Binas, Charles Blundell, Michael Mozer, Yoshua Bengio

Comments ICLR'22 accepted paper

MetaMorph: Learning Universal Controllers with Transformers

Agrim Gupta, Linxi Fan, Surya Ganguli, Li Fei-Fei

Comments ICLR 2022

Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation

Todor Davchev, Oleg Sushkov, Jean-Baptiste Regli, Stefan Schaal, Yusuf Aytar, Markus Wulfmeier, Jon Scholz

Journal ref International Conference on Learning Representations (ICLR 2022)

EigenGame Unloaded: When playing games is better than optimizing

Ian Gemp, Brian McWilliams, Claire Vernade, Thore Graepel

Comments Published in ICLR '22

Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception

Yurong You, Katie Z Luo, Xiangyu Chen, Junan Chen, Wei-Lun Chao, Wen Sun, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger

Comments Accepted by ICLR 2022. Code is available at https://github.com/YurongYou/Hindsight

The MultiBERTs: BERT Reproductions for Robustness Analysis

Thibault Sellam, Steve Yadlowsky, Jason Wei, Naomi Saphra, Alexander D'Amour, Tal Linzen, Jasmijn Bastings, Iulia Turc, Jacob Eisenstein, Dipanjan Das, Ian Tenney, Ellie Pavlick

Comments Accepted at ICLR'22. Checkpoints and example analyses: http://goo.gle/multiberts

Automated Self-Supervised Learning for Graphs

Wei Jin, Xiaorui Liu, Xiangyu Zhao, Yao Ma, Neil Shah, Jiliang Tang

Comments ICLR 2022

One After Another: Learning Incremental Skills for a Changing World

Nur Muhammad Shafiullah, Lerrel Pinto

Comments To be published in The International Conference on Learning Representations (ICLR) 2022

PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication

Cheng Wan, Youjie Li, Cameron R. Wolfe, Anastasios Kyrillidis, Nam Sung Kim, Yingyan Lin

Comments ICLR 2022

On Robust Prefix-Tuning for Text Classification

Zonghan Yang, Yang Liu

Comments Accepted in ICLR 2022. We release the code at https://github.com/minicheshire/Robust-Prefix-Tuning

Representation-Agnostic Shape Fields

Xiaoyang Huang, Jiancheng Yang, Yanjun Wang, Ziyu Chen, Linguo Li, Teng Li, Bingbing Ni, Wenjun Zhang

Comments The Tenth International Conference on Learning Representations (ICLR 2022). Code is available at https://github.com/seanywang0408/RASF

Journal ref published in the Tenth International Conference on Learning Representations (ICLR 2022)

Half-Inverse Gradients for Physical Deep Learning

Patrick Schnell, Philipp Holl, Nils Thuerey

Comments ICLR 2022 spotlight, code available at https://github.com/tum-pbs/half-inverse-gradients

Learning Features with Parameter-Free Layers

Dongyoon Han, YoungJoon Yoo, Beomyoung Kim, Byeongho Heo

Comments ICLR 2022

A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion

Zhaoyang Lyu, Zhifeng Kong, Xudong Xu, Liang Pan, Dahua Lin

Comments Accepted to ICLR 2022. Code is released at https://github.com/ZhaoyangLyu/Point_Diffusion_Refinement

Learning-Augmented $k$-means Clustering

Jon C. Ergun, Zhili Feng, Sandeep Silwal, David P. Woodruff, Samson Zhou

Comments ICLR 2022

Phase Collapse in Neural Networks

Florentin Guth, John Zarka, Stéphane Mallat

Comments 17 pages, 2 figures

Journal ref International Conference on Learning Representations, 2022

A Neural Tangent Kernel Perspective of Infinite Tree Ensembles

Ryuichi Kanoh, Mahito Sugiyama

Comments Accepted to ICLR 2022

Learning Altruistic Behaviours in Reinforcement Learning without External Rewards

Tim Franzmeyer, Mateusz Malinowski, João F. Henriques

Comments ICLR 2022 Spotlight Presentation