ICML

Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization

Alexandre Rame, Corentin Dancette, Matthieu Cord

Comments 31 pages, 14 tables, 7 figures

Journal ref ICML 2022

Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning

Ling Yang, Shenda Hong

Comments Accepted by ICML 2022

Rethinking Graph Neural Networks for Anomaly Detection

Jianheng Tang, Jiajin Li, Ziqi Gao, Jia Li

Comments Accepted by ICML 2022. Our code and data are released at https://github.com/squareRoot3/Rethinking-Anomaly-Detection

Efficient Test-Time Model Adaptation without Forgetting

Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, Mingkui Tan

Comments 17 pages, ICML 2022, conference

VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models

Wangchunshu Zhou, Yan Zeng, Shizhe Diao, Xinsong Zhang

Comments ICML 2022, Benchmark website at https://vlue-benchmark.github.io

Generating 3D Molecules for Target Protein Binding

Meng Liu, Youzhi Luo, Kanji Uchino, Koji Maruhashi, Shuiwang Ji

Comments Accepted by ICML 2022 as a Long Presentation

Lie Point Symmetry Data Augmentation for Neural PDE Solvers

Johannes Brandstetter, Max Welling, Daniel E. Worrall

Comments Published at ICML 2022, Github: https://github.com/brandstetter-johannes/LPSDA

Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion

Ling Yang, Shenda Hong

Comments Accepted by ICML 2022

Flow-Guided Sparse Transformer for Video Deblurring

Jing Lin, Yuanhao Cai, Xiaowan Hu, Haoqian Wang, Youliang Yan, Xueyi Zou, Henghui Ding, Yulun Zhang, Radu Timofte, Luc Van Gool

Comments ICML 2022; The First Transformer-based method for Video Deblurring

Going Deeper into Permutation-Sensitive Graph Neural Networks

Zhongyu Huang, Yingheng Wang, Chaozhuo Li, Huiguang He

Comments Accepted by ICML 2022. Code is publicly available at https://github.com/zhongyu1998/PG-GNN

Self-supervised models of audio effectively explain human cortical responses to speech

Aditya R. Vaidya, Shailee Jain, Alexander G. Huth

Comments Accepted to the International Conference on Machine Learning (ICML) 2022

Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval

Pascal Notin, Mafalda Dias, Jonathan Frazer, Javier Marchena-Hurtado, Aidan Gomez, Debora S. Marks, Yarin Gal

Comments ICML 2022

Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks

Runpei Dong, Zhanhong Tan, Mengdi Wu, Linfeng Zhang, Kaisheng Ma

Comments Accepted at ICML 2022

Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation

Daniel Vial, Advait Parulekar, Sanjay Shakkottai, R. Srikant

Comments This version removes most assumptions of the prior one

Journal ref International Conference on Machine Learning (ICML) 2022

On Learning Mixture of Linear Regressions in the Non-Realizable Setting

Avishek Ghosh, Arya Mazumdar, Soumyabrata Pal, Rajat Sen

Comments To appear in ICML 2022

From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model

HeeSun Bae, Seungjae Shin, Byeonghu Na, JoonHo Jang, Kyungwoo Song, Il-Chul Moon

Comments 21 pages, 9 figures. International Conference on Machine Learning (ICML 2022), Baltimore, Jul 17, 2022

Learning Mixtures of Linear Dynamical Systems

Yanxi Chen, H. Vincent Poor

Comments Accepted to ICML 2022. arXiv v2 update: add references and experiments

Tell me why! Explanations support learning relational and causal structure

Andrew K. Lampinen, Nicholas A. Roy, Ishita Dasgupta, Stephanie C. Y. Chan, Allison C. Tam, James L. McClelland, Chen Yan, Adam Santoro, Neil C. Rabinowitz, Jane X. Wang, Felix Hill

Comments ICML 2022; 23 pages

Algorithms for the Communication of Samples

Lucas Theis, Noureldin Yosri

Comments Proceedings of the 39th International Conference on Machine Learning, 2022

Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums

Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot, John Stephan

Comments Accepted at ICML 2022

PowerGraph: Using neural networks and principal components to determine multivariate statistical power trade-offs

Ajinkya K Mulay, Sean Lane, Erin Hennes

Comments Submitted to AI4Science (ICML workshop). Not published yet

Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results

Mohamad H Danesh, Alan Fern

Comments ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning

Joint Embedding of Structural and Functional Brain Networks with Graph Neural Networks for Mental Illness Diagnosis

Yanqiao Zhu, Hejie Cui, Lifang He, Lichao Sun, Carl Yang

Comments Formal version accepted to IEEE EMBC 2022; previously presented at ICML 2021 Workshop on Computational Approaches to Mental Health (no proceedings)

Neural Inverse Kinematics

Raphael Bensadoun, Shir Gur, Nitsan Blau, Tom Shenkar, Lior Wolf

Comments Accepted to ICML 2022

Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path

Haoyuan Cai, Tengyu Ma, Simon Du

Comments ICML 2022

FedNL: Making Newton-Type Methods Applicable to Federated Learning

Mher Safaryan, Rustem Islamov, Xun Qian, Peter Richtárik

Comments 65 pages, 7 algorithms, 14 figures --- Accepted to ICML 2022

Bootstrapping Fitted Q-Evaluation for Off-Policy Inference

Botao Hao, Xiang Ji, Yaqi Duan, Hao Lu, Csaba Szepesvári, Mengdi Wang

Comments Accepted at ICML 2021

LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation

David Ireland, Giovanni Montana

Comments To appear in ICML 2022

Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits

Avishek Ghosh, Abishek Sankararaman

Comments To appear in ICML 2022

Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers

Arda Sahiner, Tolga Ergen, Batu Ozturkler, John Pauly, Morteza Mardani, Mert Pilanci

Comments 38 pages, 2 figures. To appear in ICML 2022