ICLR 2022

1,094 papers

Large Language Models Can Be Strong Differentially Private Learners

Xuechen Li, Florian Tramer, Percy Liang, Tatsunori Hashimoto

Efficiently Modeling Long Sequences with Structured State Spaces

Albert Gu, Karan Goel, Christopher Re

Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion

Kohei Miyaguchi, Takayuki Katsuki, Akira Koseki, Toshiya Iwamori

StyleAlign: Analysis and Applications of Aligned StyleGAN Models

Zongze Wu, Yotam Nitzan, Eli Shechtman, Dani Lischinski

Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Ananya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma, Percy Liang

BEiT: BERT Pre-Training of Image Transformers

Hangbo Bao, Li Dong, Songhao Piao, Furu Wei

Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space

Steeven Janny, Fabien Baradel, Natalia Neverova, Madiha Nadri, Greg Mori

Expressiveness and Approximation Properties of Graph Neural Networks

Floris Geerts, Juan L Reutter

Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting

Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin

PiCO: Contrastive Label Disambiguation for Partial Label Learning

Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu

Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling

Bo Wan, Wenjuan Han, Zilong Zheng, Tinne Tuytelaars

MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling

Yusong Wu, Ethan Manilow, Yi Deng, Rigel Swavely, Kyle Kastner

Comparing Distributions by Measuring Differences that Affect Decision Making

Shengjia Zhao, Abhishek Sinha, Yutong He, Aidan Perreault, Jiaming Song

Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks

S Chandra Mouli, Bruno Ribeiro

Extending the WILDS Benchmark for Unsupervised Adaptation

Shiori Sagawa, Pang Wei Koh, Tony Lee, Irena Gao, Sang Michael Xie

iLQR-VAE : control-based learning of input-driven dynamics with applications to neural data

Marine Schimel, Ta-Chu Kao, Kristopher T Jensen, Guillaume Hennequin

Weighted Training for Cross-Task Learning

Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J Su

Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path

X.Y. Han, Vardan Papyan, David L. Donoho

Poisoning and Backdooring Contrastive Learning

Nicholas Carlini, Andreas Terzis

Data-Efficient Graph Grammar Learning for Molecular Generation

Minghao Guo, Veronika Thost, Beichen Li, Payel Das, Jie Chen

Coordination Among Neural Modules Through a Shared Global Workspace

Anirudh Goyal, Aniket Rajiv Didolkar, Alex Lamb, Kartikeya Badola, Nan Rosemary Ke

Bootstrapped Meta-Learning

Sebastian Flennerhag, Yannick Schroecker, Tom Zahavy, Hado van Hasselt, David Silver

Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics

Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford

The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions

Yifei Wang, Jonathan Lacotte, Mert Pilanci

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

Chulhee Yun, Shashank Rajput, Suvrit Sra

A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?"

Asiri Wijesinghe, Qing Wang

Neural Structured Prediction for Inductive Node Classification

Meng Qu, Huiyu Cai, Jian Tang

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization

Lixu Wang, Shichao Xu, Ruiqi Xu, Xiao Wang, Qi Zhu

Natural Language Descriptions of Deep Visual Features

Evan Hernandez, Sarah Schwettmann, David Bau, Teona Bagashvili, Antonio Torralba

Domino: Discovering Systematic Errors with Cross-Modal Embeddings

Sabri Eyuboglu, Maya Varma, Khaled Kamal Saab, Jean-Benoit Delbrouck, Christopher Lee-Messer

Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning

Yulun Zhang, Huan Wang, Can Qin, Yun Fu

Towards Building A Group-based Unsupervised Representation Disentanglement Framework

Tao Yang, Xuanchi Ren, Yuwang Wang, Wenjun Zeng, Nanning Zheng

Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View

Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng

Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring

Seungjun Nah, Sanghyun Son, Jaerin Lee, Kyoung Mu Lee

Multi-Critic Actor Learning: Teaching RL Policies to Act with Style

Siddharth Mysore, George Cheng, Yunqi Zhao, Kate Saenko, Meng Wu

Incremental False Negative Detection for Contrastive Learning

Tsai-Shien Chen, Wei-Chih Hung, Hung-Yu Tseng, Shao-Yi Chien, Ming-Hsuan Yang

Who Is Your Right Mixup Partner in Positive and Unlabeled Learning

Changchun Li, Ximing Li, Lei Feng, Jihong Ouyang

Learning Synthetic Environments and Reward Networks for Reinforcement Learning

Fabio Ferreira, Thomas Nierhoff, Andreas Sälinger, Frank Hutter

Representation-Agnostic Shape Fields

Xiaoyang Huang, Jiancheng YANG, Yanjun Wang, Ziyu Chen, Linguo Li

Feature Kernel Distillation

Bobby He, Mete Ozay

BiBERT: Accurate Fully Binarized BERT

Haotong Qin, Yifu Ding, Mingyuan Zhang, Qinghua Yan, Aishan Liu

ViDT: An Efficient and Effective Fully Transformer-based Object Detector

Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han

Boosted Curriculum Reinforcement Learning

Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Xiaojian Ma, Weili Nie, Zhiding Yu, Huaizu Jiang, Chaowei Xiao

MAML is a Noisy Contrastive Learner in Classification

Chia Hsiang Kao, Wei-Chen Chiu, Pin-Yu Chen

Memory Replay with Data Compression for Continual Learning

Liyuan Wang, Xingxing Zhang, Kuo Yang, Longhui Yu, Chongxuan Li

Denoising Likelihood Score Matching for Conditional Score-based Data Generation

Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, Yi-Chen Lo, Chia-Che Chang

Learning Features with Parameter-Free Layers

Dongyoon Han, YoungJoon Yoo, beomyoung kim, Byeongho Heo

Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies

Alon Berliner, Guy Rotman, Yossi Adi, Roi Reichart, Tamir Hazan

Transformers Can Do Bayesian Inference

Samuel Müller, Noah Hollmann, Sebastian Pineda Arango, Josif Grabocka, Frank Hutter

Rethinking Adversarial Transferability from a Data Distribution Perspective

Yao Zhu, Jiacheng Sun, Zhenguo Li

Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games

Stefanos Leonardos, Will Overman, Ioannis Panageas, Georgios Piliouras

Random matrices in service of ML footprint: ternary random features with no performance loss

Hafiz Tiomoko Ali, Zhenyu Liao, Romain Couillet

Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning

Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang

Switch to Generalize: Domain-Switch Learning for Cross-Domain Few-Shot Classification

Zhengdong Hu, Yifan Sun, Yi Yang

Online Coreset Selection for Rehearsal-based Continual Learning

Jaehong Yoon, Divyam Madaan, Eunho Yang, Sung Ju Hwang

GradMax: Growing Neural Networks using Gradient Information

Utku Evci, Bart van Merrienboer, Thomas Unterthiner, Fabian Pedregosa, Max Vladymyrov

Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing

Iro Laina, Yuki M Asano, Andrea Vedaldi

SketchODE: Learning neural sketch representation in continuous time

Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song

Learning to Schedule Learning rate with Graph Neural Networks

Yuanhao Xiong, Li-Cheng Lan, Xiangning Chen, Ruochen Wang, Cho-jui Hsieh

Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains

Qilong Zhang, Xiaodan Li, YueFeng Chen, Jingkuan Song, Lianli Gao

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

Tongkun Xu, Weihua Chen, Pichao WANG, Fan Wang, Hao Li

Variational oracle guiding for reinforcement learning

Dongqi Han, Tadashi Kozuno, Xufang Luo, Zhao-Yun Chen, Kenji Doya

Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality

Yiping Lu, Haoxuan Chen, Jianfeng Lu, Lexing Ying, Jose Blanchet

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

Yash Mehta, Colin White, Arber Zela, Arjun Krishnakumar, Guri Zabergja

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks

Tianjun Zhang, Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Joseph E. Gonzalez

Neural graphical modelling in continuous-time: consistency guarantees and algorithms

Alexis Bellot, Kim Branson, Mihaela van der Schaar

VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects

Ruihai Wu, Yan Zhao, Kaichun Mo, Zizheng Guo, Yian Wang

IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes

Qi Li, Kaichun Mo, Yanchao Yang, Hang Zhao, Leonidas Guibas

GNN is a Counter? Revisiting GNN for Question Answering

Kuan Wang, Yuyu Zhang, Diyi Yang, Le Song, Tao Qin

Dual Lottery Ticket Hypothesis

Yue Bai, Huan Wang, Zhiqiang Tao, Kunpeng Li, Yun Fu

Entroformer: A Transformer-based Entropy Model for Learned Image Compression

Yichen Qian, Xiuyu Sun, Ming Lin, Zhiyu Tan, Rong Jin

On the Importance of Difficulty Calibration in Membership Inference Attacks

Lauren Watson, Chuan Guo, Graham Cormode, Alexandre Sablayrolles

Know Your Action Set: Learning Action Relations for Reinforcement Learning

Ayush Jain, Norio Kosaka, Kyung-Min Kim, Joseph J Lim

Shuffle Private Stochastic Convex Optimization

Albert Cheu, Matthew Joseph, Jieming Mao, Binghui Peng

InfinityGAN: Towards Infinite-Pixel Image Synthesis

Chieh Hubert Lin, Hsin-Ying Lee, Yen-Chi Cheng, Sergey Tulyakov, Ming-Hsuan Yang

Skill-based Meta-Reinforcement Learning

Taewook Nam, Shao-Hua Sun, Karl Pertsch, Sung Ju Hwang, Joseph J Lim

Chemical-Reaction-Aware Molecule Representation Learning

Hongwei Wang, Weijiang Li, Xiaomeng Jin, Kyunghyun Cho, Heng Ji

Visual Representation Learning over Latent Domains

Lucas Deecke, Timothy Hospedales, Hakan Bilen

Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval

Binjie Zhang, Yixiao Ge, Yantao Shen, Yu Li, Chun Yuan

Adversarially Robust Conformal Prediction

Asaf Gendler, Tsui-Wei Weng, Luca Daniel, Yaniv Romano

CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention

Wenxiao Wang, Lu Yao, Long Chen, Binbin Lin, Deng Cai

Neural Markov Controlled SDE: Stochastic Optimization for Continuous-Time Data

Sung Woo Park, Kyungjae Lee, Junseok Kwon

Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

Dacheng Yin, Xuanchi Ren, Chong Luo, Yuwang Wang, Zhiwei Xiong

Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection

Wei Ji, Jingjing Li, Qi Bi, Chuan Guo, Jie Liu

β-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap

Pengzhou Abel Wu, Kenji Fukumizu

Deep Point Cloud Reconstruction

Jaesung Choe, ByeongIn Joung, Francois Rameau, Jaesik Park, In So Kweon

Few-shot Learning via Dirichlet Tessellation Ensemble

Chunwei Ma, Ziyun Huang, Mingchen Gao, Jinhui Xu

Permutation Compressors for Provably Faster Distributed Nonconvex Optimization

Rafał Szlendak, Alexander Tyurin, Peter Richtarik

OntoProtein: Protein Pretraining With Gene Ontology Embedding

Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

Ningyu Zhang, Luoqiu Li, Xiang Chen, Shumin Deng, Zhen Bi

A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of Disease

Sayan Ghosal, Qiang Chen, Giulio Pergola, Aaron L Goldman, William Ulrich

How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data

Zhiyuan Zhang, Lingjuan Lyu, Weiqiang Wang, Lichao Sun, Xu Sun

Neural Spectral Marked Point Processes

Shixiang Zhu, Haoyun Wang, Zheng Dong, Xiuyuan Cheng, Yao Xie

Divergence-aware Federated Self-Supervised Learning

Weiming Zhuang, Yonggang Wen, SHUAI ZHANG

Steerable Partial Differential Operators for Equivariant Neural Networks

Erik Jenner, Maurice Weiler

Fixed Neural Network Steganography: Train the images, not the network

Varsha Kishore, Xiangyu Chen, Yan Wang, Boyi Li, Kilian Q Weinberger

DKM: Differentiable k-Means Clustering Layer for Neural Network Compression

Minsik Cho, Keivan Alizadeh-Vahid, Saurabh Adya, Mohammad Rastegari

Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning

Samet Cetin, Orhun Buğra Baran, Ramazan Gokberk Cinbis

Generalized Demographic Parity for Group Fairness

Zhimeng Jiang, Xiaotian Han, Chao Fan, Fan Yang, Ali Mostafavi