ICML

AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation

Yi-Fan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan

Comments 30 pages, 12 figures

Journal ref The Fortieth International Conference on Machine Learning, ICML, 2023

Progressive Purification for Instance-Dependent Partial Label Learning

Ning Xu, Biao Liu, Jiaqi Lv, Congyu Qiao, Xin Geng

Comments Accepted to International Conference on Machine Learning 2023 (ICML 2023)

FAENet: Frame Averaging Equivariant GNN for Materials Modeling

Alexandre Duval, Victor Schmidt, Alex Hernandez Garcia, Santiago Miret, Fragkiskos D. Malliaros, Yoshua Bengio, David Rolnick

Comments Accepted at ICML 2023

From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks

Cai Zhou, Xiyuan Wang, Muhan Zhang

Comments To be published in ICML 2023. 27 pages, 5 figures

CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations

Gengchen Mai, Ni Lao, Yutong He, Jiaming Song, Stefano Ermon

Comments In: ICML 2023, Jul 23 - 29, 2023, Honolulu, Hawaii, USA

Proximal Causal Learning of Conditional Average Treatment Effects

Erik Sverdrup, Yifan Cui

Comments ICML 2023

Escaping saddle points in zeroth-order optimization: the power of two-point estimators

Zhaolin Ren, Yujie Tang, Na Li

Comments To appear at ICML 2023

Bit Allocation using Optimization

Tongda Xu, Han Gao, Chenjian Gao, Yuanyuan Wang, Dailan He, Jinyong Pi, Jixiang Luo, Ziyu Zhu, Mao Ye, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang

Comments ICML 2023

Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning

Yulai Zhao, Zhuoran Yang, Zhaoran Wang, Jason D. Lee

Comments ICML 2023

BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning

Kishaan Jeeveswaran, Prashant Bhat, Bahram Zonooz, Elahe Arani

Comments Accepted at 40th International Conference on Machine Learning (ICML 2023)

Behavior Contrastive Learning for Unsupervised Skill Discovery

Rushuai Yang, Chenjia Bai, Hongyi Guo, Siyuan Li, Bin Zhao, Zhen Wang, Peng Liu, Xuelong Li

Comments Accepted at the 40th International Conference on Machine Learning (ICML 2023)

Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering

Erlin Pan, Zhao Kang

Comments Accepted by ICML 2023

Deep Graph Representation Learning and Optimization for Influence Maximization

Chen Ling, Junji Jiang, Junxiang Wang, My Thai, Lukas Xue, James Song, Meikang Qiu, Liang Zhao

Comments In Proceedings of the 40th International Conference on Machine Learning (ICML 2023), Honolulu, Hawaii, USA. PMLR 202, 2023

Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction

Khai Nguyen, Dang Nguyen, Nhat Ho

Comments Accepted to ICML 2023, 23 pages, 6 figures, 9 tables,

Learning-Augmented Private Algorithms for Multiple Quantile Release

Mikhail Khodak, Kareem Amin, Travis Dick, Sergei Vassilvitskii

Comments To appear in ICML 2023

TPC: Transformation-Specific Smoothing for Point Cloud Models

Wenda Chu, Linyi Li, Bo Li

Comments Accepted as a conference paper at ICML 2022

Directed Chain Generative Adversarial Networks

Ming Min, Ruimeng Hu, Tomoyuki Ichiba

Comments Publish at ICML 2023

Improving Graph Neural Networks with Learnable Propagation Operators

Moshe Eliasof, Lars Ruthotto, Eran Treister

Comments Accepted to the International Conference on Machine Learning (ICML) 2023

Mates2Motion: Learning How Mechanical CAD Assemblies Work

James Noeckel, Benjamin T. Jones, Karl Willis, Brian Curless, Adriana Schulz

Comments Contains 5 pages, 2 figures. Presented at the ICML 2022 Workshop on Machine Learning in Computational Design

Masked Trajectory Models for Prediction, Representation, and Control

Philipp Wu, Arjun Majumdar, Kevin Stone, Yixin Lin, Igor Mordatch, Pieter Abbeel, Aravind Rajeswaran

Comments Accepted for publication at ICML 2023. Project webpage: https://wuphilipp.github.io/mtm/

Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality

Dhruv Malik, Conor Igoe, Yuanzhi Li, Aarti Singh

Comments ICML 2023

Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA

Ilias Diakonikolas, Daniel M. Kane, Ankit Pensia, Thanasis Pittas

Comments To appear in ICML 2023

Attention-Based Generative Neural Image Compression on Solar Dynamics Observatory

Ali Zafari, Atefeh Khoshkhahtinat, Piyush M. Mehta, Nasser M. Nasrabadi, Barbara J. Thompson, Daniel da Silva, Michael S. F. Kirk

Comments Accepted to IEEE 21$^{st}$ International Conference on Machine Learning and Applications 2022 (ICMLA) - Selected for Oral Presentation

Representation Topology Divergence: A Method for Comparing Neural Network Representations

Serguei Barannikov, Ilya Trofimov, Nikita Balabin, Evgeny Burnaev

Journal ref Proceedings of the 39th International Conference on Machine Learning (ICML 2022), PMLR 162:1607-1626, 2022

LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning

Timothy Castiglia, Yi Zhou, Shiqiang Wang, Swanand Kadhe, Nathalie Baracaldo, Stacy Patterson

Comments Published in ICML 2023

Histogram Layers for Synthetic Aperture Sonar Imagery

Joshua Peeples, Alina Zare, Jeffrey Dale, James Keller

Comments 7 pages, 9 Figures, Accepted to IEEE International Conference on Machine Learning and Applications (ICMLA) 2022

A Closer Look at Self-Supervised Lightweight Vision Transformers

Shaoru Wang, Jin Gao, Zeming Li, Xiaoqin Zhang, Weiming Hu

Comments Accepted by ICML 2023

Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement

Ailin Deng, Miao Xiong, Bryan Hooi

Comments ICML 2023

Geometric Latent Diffusion Models for 3D Molecule Generation

Minkai Xu, Alexander Powers, Ron Dror, Stefano Ermon, Jure Leskovec

Comments Published at ICML 2023

Personalized Federated Learning under Mixture of Distributions

Yue Wu, Shuaicheng Zhang, Wenchao Yu, Yanchi Liu, Quanquan Gu, Dawei Zhou, Haifeng Chen, Wei Cheng

Comments International Conference on Machine Learning (ICML'23)