ICLR 2022

1,094 papers

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Mark Hamilton, Zhoutong Zhang, Bharath Hariharan, Noah Snavely, William T. Freeman

AdaAug: Learning Class- and Instance-adaptive Data Augmentation Policies

Tsz-Him Cheung, Dit-Yan Yeung

Bandit Learning with Joint Effect of Incentivized Sampling, Delayed Sampling Feedback, and Self-Reinforcing User Preferences

Tianchen Zhou, Jia Liu, Chaosheng Dong, Yi Sun

W-CTC: a Connectionist Temporal Classification Loss with Wild Cards

Xingyu Cai, Jiahong Yuan, Yuchen Bian, Guangxu Xun, Jiaji Huang

Provably convergent quasistatic dynamics for mean-field two-player zero-sum games

Chao Ma, Lexing Ying

EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression

Zirui Liu, Kaixiong Zhou, Fan Yang, Li Li, Rui Chen

MonoDistill: Learning Spatial Features for Monocular 3D Object Detection

Zhiyu Chong, Xinzhu Ma, Hong Zhang, Yuxin Yue, Haojie Li

Offline Reinforcement Learning with Value-based Episodic Memory

Xiaoteng Ma, Yiqin Yang, Hao Hu, Jun Yang, Chongjie Zhang

Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs

Sitan Chen, Jerry Li, Yuanzhi Li, Raghu Meka

Group-based Interleaved Pipeline Parallelism for Large-scale DNN Training

Pengcheng Yang, Xiaoming Zhang, Wenpeng Zhang, Ming Yang, Hong Wei

Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis

Siyi Tang, Jared Dunnmon, Khaled Kamal Saab, Xuan Zhang, Qianying Huang

Hindsight: Posterior-guided training of retrievers for improved open-ended generation

Ashwin Paranjape, Omar Khattab, Christopher Potts, Matei Zaharia, Christopher D Manning

A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs

Ido Nachum, Jan Hazla, Michael Gastpar, Anatoly Khina

Scale Mixtures of Neural Network Gaussian Processes

Hyungi Lee, Eunggu Yun, Hongseok Yang, Juho Lee

Model-Based Offline Meta-Reinforcement Learning with Regularization

Sen Lin, Jialin Wan, Tengyu Xu, Yingbin Liang, Junshan Zhang

Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, Yin Cui

Local Feature Swapping for Generalization in Reinforcement Learning

David Bertoin, Emmanuel Rachelson

Exploring extreme parameter compression for pre-trained language models

Benyou Wang, Yuxin Ren, Lifeng Shang, Xin Jiang, Qun Liu

Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism

Ming Yin, Yaqi Duan, Mengdi Wang, Yu-Xiang Wang

CURVATURE-GUIDED DYNAMIC SCALE NETWORKS FOR MULTI-VIEW STEREO

Khang Truong Giang, Soohwan Song, Sungho Jo

Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning

Yutong Wang, Ke Xue, Chao Qian

Enhancing Cross-lingual Transfer by Manifold Mixup

Huiyun Yang, Huadong Chen, Hao Zhou, Lei Li

Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

Quanyi Li, Zhenghao Peng, Bolei Zhou

Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

Sihyun Yu, Jihoon Tack, Sangwoo Mo, Hyunsu Kim, Junho Kim

Improving the Accuracy of Learning Example Weights for Imbalance Classification

Yuqi Liu, Bin Cao, Jing Fan

SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training

Wenyong Huang, Zhenhe Zhang, Yu Ting Yeung, Xin Jiang, Qun Liu

Phase Collapse in Neural Networks

Florentin Guth, John Zarka, Stephane Mallat

Learning to Guide and to be Guided in the Architect-Builder Problem

Paul Barde, Tristan Karch, Derek Nowrouzezahrai, Clément Moulin-Frier, Christopher Pal

Understanding and Improving Graph Injection Attack by Promoting Unnoticeability

Yongqiang Chen, Han Yang, Yonggang Zhang, MA Kaili, Tongliang Liu

Distributionally Robust Fair Principal Components via Geodesic Descents

Hieu Vu, Toan Tran, Man-Chung Yue, Viet Anh Nguyen

Adversarial Robustness Through the Lens of Causality

Yonggang Zhang, Mingming Gong, Tongliang Liu, Gang Niu, Xinmei Tian

Prototypical Contrastive Predictive Coding

Kyungmin Lee

Pareto Set Learning for Neural Multi-Objective Combinatorial Optimization

Xi Lin, Zhiyuan Yang, Qingfu Zhang

Language model compression with weighted low-rank factorization

Yen-Chang Hsu, Ting Hua, Sungen Chang, Qian Lou, Yilin Shen

Label-Efficient Semantic Segmentation with Diffusion Models

Dmitry Baranchuk, Andrey Voynov, Ivan Rubachev, Valentin Khrulkov, Artem Babenko

On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks

Maximilian Seitzer, Arash Tavakoli, Dimitrije Antić, Georg Martius

Graph Neural Network Guided Local Search for the Traveling Salesperson Problem

Benjamin Hudson, Qingbiao Li, Matthew Malencia, Amanda Prorok

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Vaisakh Shaj, Dieter Büchler, Rohit Sonker, Philipp Becker, Gerhard Neumann

Objects in Semantic Topology

Shuo Yang, Peize Sun, Yi Jiang, Xiaobo Xia, Ruiheng Zhang

Gradient Matching for Domain Generalization

Yuge Shi, Jeffrey Seely, Philip Torr, Siddharth N, Awni Hannun

Discrepancy-Based Active Learning for Domain Adaptation

Antoine de Mathelin, François Deheeger, Mathilde Mougeot, Nicolas Vayatis

Learning to Extend Molecular Scaffolds with Structural Motifs

Krzysztof Maziarz, Henry Richard Jackson-Flux, Pashmina Cameron, Finton Sirockin, Nadine Schneider

DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations

Geon-hyeong Kim, Seokin Seo, Jongmin Lee, Wonseok Jeon, HyeongJoo Hwang

Neural Stochastic Dual Dynamic Programming

Hanjun Dai, Yuan Xue, Zia Syed, Dale Schuurmans, Bo Dai

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

Martin Mundt, Steven Lang, Quentin Delfosse, Kristian Kersting

THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou, Bogdan Stanciulescu, Fabien Moutarde

Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization

Thanh Nguyen-Tang, Sunil Gupta, A. Tuan Nguyen, Svetha Venkatesh

Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs

Andjela Mladenovic, Iosif Sakos, Gauthier Gidel, Georgios Piliouras

LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations

Jaehoon Lee, Jinsung Jeon, Sheo Yon Jhin, Jihyeon Hyeong, Jayoung Kim

Multi-Mode Deep Matrix and Tensor Factorization

Jicong Fan

Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies

Alex Chan, Alicia Curth, Mihaela van der Schaar

UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning

Kunchang Li, Yali Wang, Gao Peng, Guanglu Song, Yu Liu

Target-Side Input Augmentation for Sequence to Sequence Generation

Shufang Xie, Ang Lv, Yingce Xia, Lijun Wu, Tao Qin

PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior

Sang-gil Lee, Heeseung Kim, Chaehun Shin, Xu Tan, Chang Liu

Optimal Transport for Long-Tailed Recognition with Learnable Cost Matrix

Hanyu Peng, Mingming Sun, Ping Li

Reinforcement Learning in Presence of Discrete Markovian Context Evolution

Hang Ren, Aivar Sootla, Taher Jafferjee, Junxiao Shen, Jun Wang

Inductive Relation Prediction Using Analogy Subgraph Embeddings

Jiarui Jin, Yangkun Wang, Kounianhua Du, Weinan Zhang, Zheng Zhang

Attention-based Interpretability with Concept Transformers

Mattia Rigotti, Christoph Miksovic, Ioana Giurgiu, Thomas Gschwind, Paolo Scotton

How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning

Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Trung X. Pham, Chang D. Yoo

Gaussian Mixture Convolution Networks

Adam Celarek, Pedro Hermosilla, Bernhard Kerbl, Timo Ropinski, Michael Wimmer

ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity

Xinchi Qiu, Javier Fernández-Marqués, Pedro PB Gusmao, Yan Gao, Titouan Parcollet

Learning a subspace of policies for online adaptation in Reinforcement Learning

Jean-Baptiste Gaya, Laure Soulier, Ludovic DENOYER

TAda! Temporally-Adaptive Convolutions for Video Understanding

Ziyuan Huang, Shiwei Zhang, Liang Pan, Zhiwu Qing, Mingqian Tang

Better Supervisory Signals by Observing Learning Paths

Yi Ren, Shangmin Guo, Danica J. Sutherland

ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind

Yuanfei Wang, Fangwei Zhong, Jing Xu, Yizhou Wang

PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series

Paul Jeha, Michael Bohlke-Schneider, Pedro Mercado, Shubham Kapoor, Rajbir Singh Nirwan

Neural Solvers for Fast and Accurate Numerical Optimal Control

Federico Berto, Stefano Massaroli, Michael Poli, Jinkyoo Park

Query Embedding on Hyper-Relational Knowledge Graphs

Dimitrios Alivanistos, Max Berrendorf, Michael Cochez, Mikhail Galkin

On the Pitfalls of Analyzing Individual Neurons in Language Models

Omer Antverg, Yonatan Belinkov

Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift

Taesung Kim, Jinhee Kim, Yunwon Tae, Cheonbok Park, Jang-Ho Choi

Fast Generic Interaction Detection for Model Interpretability and Compression

Tianjian Zhang, Feng Yin, Zhi-Quan Luo

Unrolling PALM for Sparse Semi-Blind Source Separation

Mohammad Fahes, Christophe Kervazo, Jérôme Bobin, Florence Tupin

Stability Regularization for Discrete Representation Learning

Adeel Pervez, Efstratios Gavves

Bag of Instances Aggregation Boosts Self-supervised Distillation

Haohang Xu, Jiemin Fang, XIAOPENG ZHANG, Lingxi Xie, Xinggang Wang

Igeood: An Information Geometry Approach to Out-of-Distribution Detection

Eduardo Dadalto Camara Gomes, Florence Alberge, Pierre Duhamel, Pablo Piantanida

Actor-critic is implicitly biased towards high entropy optimal policies

Yuzheng Hu, Ziwei Ji, Matus Telgarsky

Knowledge Removal in Sampling-based Bayesian Inference

Shaopeng Fu, Fengxiang He, Dacheng Tao

Regularized Autoencoders for Isometric Representation Learning

Yonghyeon LEE, Sangwoong Yoon, MinJun Son, Frank C. Park

Charformer: Fast Character Transformers via Gradient-based Subword Tokenization

Yi Tay, Vinh Q. Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung

GPT-Critic: Offline Reinforcement Learning for End-to-End Task-Oriented Dialogue Systems

Youngsoo Jang, Jongmin Lee, Kee-eung Kim

A Deep Variational Approach to Clustering Survival Data

Laura Manduchi, Ričards Marcinkevičs, Michela C. Massi, Thomas Weikert, Alexander Sauter

Generative Pseudo-Inverse Memory

Kha Pham, Hung Le, Man Ngo, Truyen Tran, Bao Ho

What Makes Better Augmentation Strategies? Augment Difficult but Not too Different

Jaehyung Kim, Dongyeop Kang, Sungsoo Ahn, Jinwoo Shin

Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions

Moise Blanchard, Mohammed Amine Bennouna

BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models

Kangjie Chen, Yuxian Meng, Xiaofei Sun, Shangwei Guo, Tianwei Zhang

Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks

Haorui Wang, Haoteng YIN, Muhan Zhang, Pan Li

A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training

Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin

Maximum Entropy RL (Provably) Solves Some Robust RL Problems

Benjamin Eysenbach, Sergey Levine

Learning by Directional Gradient Descent

David Silver, Anirudh Goyal, Ivo Danihelka, Matteo Hessel, Hado van Hasselt

Why Propagate Alone? Parallel Use of Labels and Features on Graphs

Yangkun Wang, Jiarui Jin, Weinan Zhang, Yang Yongyi, Jiuhai Chen

Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting

Hyunwook Lee, Seungmin Jin, Hyeshin Chu, Hongkyu Lim, Sungahn Ko

Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization

Zihan Zhou, Wei Fu, Bingliang Zhang, Yi Wu

GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification

Joonhyung Park, Jaeyun Song, Eunho Yang

GeneDisco: A Benchmark for Experimental Design in Drug Discovery

Arash Mehrjou, Ashkan Soleymani, Andrew Jesson, Pascal Notin, Yarin Gal

End-to-End Learning of Probabilistic Hierarchies on Graphs

Daniel Zügner, Bertrand Charpentier, Morgane Ayle, Sascha Geringer, Stephan Günnemann

Hierarchical Few-Shot Imitation with Skill Transition Models

Kourosh Hakhamaneshi, Ruihan Zhao, Albert Zhan, Pieter Abbeel, Michael Laskin

Evaluating Model-Based Planning and Planner Amortization for Continuous Control

Arunkumar Byravan, Leonard Hasenclever, Piotr Trochim, Mehdi Mirza, Alessandro Davide Ialongo

Differentiable DAG Sampling

Bertrand Charpentier, Simon Kibler, Stephan Günnemann

Salient ImageNet: How to discover spurious features in Deep Learning?

Sahil Singla, Soheil Feizi

Pretrained Language Model in Continual Learning: A Comparative Study

Tongtong Wu, Massimo Caccia, Zhuang Li, Yuan-Fang Li, Guilin Qi