ICLR

DISSECT: Disentangled Simultaneous Explanations via Concept Traversals

Asma Ghandeharioun, Been Kim, Chun-Liang Li, Brendan Jou, Brian Eoff, Rosalind W. Picard

Comments Accepted for publication at ICLR 2022

Towards Building A Group-based Unsupervised Representation Disentanglement Framework

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

Comments Accepted by ICLR 2022

Phenomenology of Double Descent in Finite-Width Neural Networks

Sidak Pal Singh, Aurelien Lucchi, Thomas Hofmann, Bernhard Schölkopf

Comments Published at ICLR 2022

DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning

Jinxin Liu, Hongyin Zhang, Donglin Wang

Comments ICLR 2022

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

Qilong Zhang, Xiaodan Li, Yuefeng Chen, Jingkuan Song, Lianli Gao, Yuan He, Hui Xue

Comments Accepted by ICLR 2022

Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction

Bowen Shi, Wei-Ning Hsu, Kushal Lakhotia, Abdelrahman Mohamed

Comments ICLR 2022

Contrastive Fine-grained Class Clustering via Generative Adversarial Networks

Yunji Kim, Jung-Woo Ha

Comments ICLR 2022

Fast Topological Clustering with Wasserstein Distance

Tananun Songdechakraiwut, Bryan M. Krause, Matthew I. Banks, Kirill V. Nourski, Barry D. Van Veen

Comments Published at the 10th International Conference on Learning Representations (ICLR 2022); 18 pages, 10 figures

Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization

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

Comments A full version at ICLR'22; a preliminary version at Offline RL Workshop at NeurIPS'21; code: https://github.com/thanhnguyentang/offline_neural_bandits

Journal ref ICLR 2022

Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks

Morteza Ramezani, Weilin Cong, Mehrdad Mahdavi, Mahmut T. Kandemir, Anand Sivasubramaniam

Comments The Tenth International Conference on Learning Representations (ICLR 2022)

Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

Wenqing Zheng, Edward W Huang, Nikhil Rao, Sumeet Katariya, Zhangyang Wang, Karthik Subbian

Comments Published as a conference paper in ICLR 2022

Crystal Diffusion Variational Autoencoder for Periodic Material Generation

Tian Xie, Xiang Fu, Octavian-Eugen Ganea, Regina Barzilay, Tommi Jaakkola

Comments Accepted to ICLR 2022. Code and data are publicly available at https://github.com/txie-93/cdvae

Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

Fangyu Liu, Yunlong Jiao, Jordan Massiah, Emine Yilmaz, Serhii Havrylov

Comments ICLR 2022; code and models are released at https://github.com/amzn/trans-encoder

TAPEX: Table Pre-training via Learning a Neural SQL Executor

Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, Jian-Guang Lou

Comments ICLR 2022 camera ready version

MAML is a Noisy Contrastive Learner in Classification

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

Comments 22 pages, 17 figures. Accepted by ICLR 2022

Data Poisoning Won't Save You From Facial Recognition

Evani Radiya-Dixit, Sanghyun Hong, Nicholas Carlini, Florian Tramèr

Comments ICLR 2022

Shuffle Private Stochastic Convex Optimization

Albert Cheu, Matthew Joseph, Jieming Mao, Binghui Peng

Comments Accepted to ICLR 2022

Churn Reduction via Distillation

Heinrich Jiang, Harikrishna Narasimhan, Dara Bahri, Andrew Cotter, Afshin Rostamizadeh

Journal ref ICLR 2022

Exploring Memorization in Adversarial Training

Yinpeng Dong, Ke Xu, Xiao Yang, Tianyu Pang, Zhijie Deng, Hang Su, Jun Zhu

Comments Accepted by ICLR 2022. 24 pages

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

Xiangning Chen, Cho-Jui Hsieh, Boqing Gong

Comments ICLR 2022 (spotlight)

Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis

Siyi Tang, Jared A. Dunnmon, Khaled Saab, Xuan Zhang, Qianying Huang, Florian Dubost, Daniel L. Rubin, Christopher Lee-Messer

Comments Published as a conference paper at ICLR 2022

Journal ref ICLR 2022

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

Runtian Zhai, Chen Dan, Di He, Huan Zhang, Boqing Gong, Pradeep Ravikumar, Cho-Jui Hsieh, Liwei Wang

Comments Published in ICLR 2020. 20 Pages

BiBERT: Accurate Fully Binarized BERT

Haotong Qin, Yifu Ding, Mingyuan Zhang, Qinghua Yan, Aishan Liu, Qingqing Dang, Ziwei Liu, Xianglong Liu

Journal ref International Conference on Learning Representations (ICLR) 2022

Language-biased image classification: evaluation based on semantic representations

Yoann Lemesle, Masataka Sawayama, Guillermo Valle-Perez, Maxime Adolphe, Hélène Sauzéon, Pierre-Yves Oudeyer

Comments Accepted at ICLR 2022

Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice

Peihao Wang, Wenqing Zheng, Tianlong Chen, Zhangyang Wang

Comments International Conference on Learning Representations (ICLR), 2022

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

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

Comments ICLR 2022

A Generalized Weighted Optimization Method for Computational Learning and Inversion

Björn Engquist, Kui Ren, Yunan Yang

Comments 25 pages, 2 figures; Published as a conference paper at ICLR 2022. In International Conference on Learning Representations (2022)

Towards Empirical Sandwich Bounds on the Rate-Distortion Function

Yibo Yang, Stephan Mandt

Comments ICLR 2022 camera-ready version

Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction

Eli Chien, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Jiong Zhang, Olgica Milenkovic, Inderjit S Dhillon

Comments Published in ICLR 2022

InfinityGAN: Towards Infinite-Pixel Image Synthesis

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

Comments Accepted to ICLR 2022. Full Paper: https://openreview.net/forum?id=ufGMqIM0a4b ; Project page: https://hubert0527.github.io/infinityGAN/