ICLR

Adversarial Unlearning of Backdoors via Implicit Hypergradient

Yi Zeng, Si Chen, Won Park, Z. Morley Mao, Ming Jin, Ruoxi Jia

Comments In proceeding of the Tenth International Conference on Learning Representations (ICLR 2022)

Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory

Jason Ramapuram, Yan Wu, Alexandros Kalousis

Journal ref ICLR 2021

Robust Audio Anomaly Detection

Wo Jae Lee, Karim Helwani, Arvindh Krishnaswamy, Srikanth Tenneti

Comments Accepted paper at RobustML Workshop@ICLR 2021

Journal ref RobustML Workshop - ICLR 2021

Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks

Anne Harrington, Arturo Deza

Comments Accepted to ICLR 2022 as a Spotlight

Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning

Haichao Zhang, Wei Xu, Haonan Yu

Comments Spotlight paper at the 10th International Conference on Learning Representations (ICLR 2022)

Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation

Yan Zhang, David W. Zhang, Simon Lacoste-Julien, Gertjan J. Burghouts, Cees G. M. Snoek

Comments Published at International Conference on Learning Representations (ICLR) 2022

Neural Networks as Kernel Learners: The Silent Alignment Effect

Alexander Atanasov, Blake Bordelon, Cengiz Pehlevan

Comments 29 pages, 15 figures. Added additional experiments and expanded the derivations in the appendix

Journal ref ICLR 2022

Data-Driven Offline Optimization For Architecting Hardware Accelerators

Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine

Comments First two authors contributed equally; published at ICLR 2022

Taming Sparsely Activated Transformer with Stochastic Experts

Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan, Ruofei Zhang, Tuo Zhao, Jianfeng Gao

Comments ICLR 2022

How many degrees of freedom do we need to train deep networks: a loss landscape perspective

Brett W. Larsen, Stanislav Fort, Nic Becker, Surya Ganguli

Comments ICLR 2022

Variational Neural Cellular Automata

Rasmus Berg Palm, Miguel González-Duque, Shyam Sudhakaran, Sebastian Risi

Comments ICLR 2022

Towards a Unified View of Parameter-Efficient Transfer Learning

Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig

Comments ICLR 2022 (spotlight presentation). Code is available at https://github.com/jxhe/unify-parameter-efficient-tuning

Autoregressive Diffusion Models

Emiel Hoogeboom, Alexey A. Gritsenko, Jasmijn Bastings, Ben Poole, Rianne van den Berg, Tim Salimans

Comments Published as a conference paper at International Conference on Learning Representations (ICLR) 2022

NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs

Mikhail Galkin, Etienne Denis, Jiapeng Wu, William L. Hamilton

Comments Accepted to ICLR 2022

Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields

Wang Yifan, Lukas Rahmann, Olga Sorkine-Hornung

Comments Accepted to ICLR 2022, 20 pages including appendix. Code available at https://github.com/yifita/idf

Capturing Structural Locality in Non-parametric Language Models

Frank F. Xu, Junxian He, Graham Neubig, Vincent J. Hellendoorn

Comments ICLR 2022

Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?

Sheikh Shams Azam, Seyyedali Hosseinalipour, Qiang Qiu, Christopher Brinton

Comments In Proceedings of the 10th International Conference on Learning Representations (ICLR) 2022

Fortuitous Forgetting in Connectionist Networks

Hattie Zhou, Ankit Vani, Hugo Larochelle, Aaron Courville

Comments ICLR Camera Ready

Journal ref ICLR 2022

CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability

Martin Mundt, Steven Lang, Quentin Delfosse, Kristian Kersting

Comments International Conference on Learning Representations (ICLR) 2022

Learning Super-Features for Image Retrieval

Philippe Weinzaepfel, Thomas Lucas, Diane Larlus, Yannis Kalantidis

Comments ICLR 2022

Discovering Invariant Rationales for Graph Neural Networks

Ying-Xin Wu, Xiang Wang, An Zhang, Xiangnan He, Tat-Seng Chua

Comments ICLR 2022

ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning

Vamsi Aribandi, Yi Tay, Tal Schuster, Jinfeng Rao, Huaixiu Steven Zheng, Sanket Vaibhav Mehta, Honglei Zhuang, Vinh Q. Tran, Dara Bahri, Jianmo Ni, Jai Gupta, Kai Hui, Sebastian Ruder, Donald Metzler

Comments ICLR 2022; see https://youtu.be/FbRcbM4T-50 for a video overview of the paper

Hybrid Random Features

Krzysztof Choromanski, Haoxian Chen, Han Lin, Yuanzhe Ma, Arijit Sehanobish, Deepali Jain, Michael S Ryoo, Jake Varley, Andy Zeng, Valerii Likhosherstov, Dmitry Kalashnikov, Vikas Sindhwani, Adrian Weller

Comments Published as a conference paper at ICLR 2022

Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers

Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler

Comments ICLR 2022 + Updated Checkpoint Release

How Attentive are Graph Attention Networks?

Shaked Brody, Uri Alon, Eran Yahav

Comments Published in ICLR 2022

Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression

Baeseong Park, Se Jung Kwon, Daehwan Oh, Byeongwook Kim, Dongsoo Lee

Comments ICLR 2022 Accepted

Bootstrapping Semantic Segmentation with Regional Contrast

Shikun Liu, Shuaifeng Zhi, Edward Johns, Andrew J. Davison

Comments Published at ICLR 2022. Project Page: https://shikun.io/projects/regional-contrast. Code: https://github.com/lorenmt/reco

VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

Adrien Bardes, Jean Ponce, Yann LeCun

Comments Accepted at ICLR 2022

Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design

Wengong Jin, Jeremy Wohlwend, Regina Barzilay, Tommi Jaakkola

Comments Accepted to ICLR 2022

Controlling Directions Orthogonal to a Classifier

Yilun Xu, Hao He, Tianxiao Shen, Tommi Jaakkola

Comments accepted by ICLR 2022