革新知能統合研究センター

2024年6月11日更新

機械学習のトップカンファレンスである International Conference on Machine Learning (ICML) 2024において、AIPセンターから37本の論文が採択されました。

[Website]https://icml.cc/Conferences/2024/
[Accepted Papers] https://openreview.net/group?id=ICML.cc/2024/Conference#tab-accept

参考：ICML2024では、9473本の論文投稿があり、2609本の論文が採択（採択率27.5％）されました。
[採択率]
Poster Presentation:27.5% (2609/9473)
Spotlight Presentation:3.5% (144+191/9473)
Oral Presentation:1.5% (144/9473)

Oral Presentation

• Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
  Juno Kim (The University of Tokyo / RIKEN AIP)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)

Spotlight Presentation

• Locally Estimated Global Perturbations is Better than Local Perturbations for Federated Sharpness-aware Minimization
  Ziqing Fan (Shanghai Jiaotong University)
  Shengchao Hu (Shanghai Jiaotong University)
  Jiangchao Yao (Shanghai Jiaotong University)
  Gang Niu (RIKEN AIP)
  Ya Zhang (Shanghai Jiaotong University)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Yanfeng Wang (Shanghai Jiaotong University)
• Variational Learning is Effective for Large Deep Networks
  Yuesong Shen* (Technical University Munich)
  Nico Daheim* (Technical University Darmstadt)
  Bai Cong (Tokyo Institute of Technology)
  Peter Nickl (RIKEN AIP)
  Gian Maria Marconi (RIKEN AIP)
  Clement Bazan (Tokyo Institute of Technology)
  Rio Yokota (Tokyo Institute of Technology)
  Iryna Gurevych (Technical University Munich)
  Daniel Cremers(Technical University Darmstadt)
  Mohammad Emtiyaz Khan (RIKEN AIP)
  Thomas Möllenhoff (RIKEN AIP)
  ** Equal contribution

Poster Presentation

• Adversarially Robust Deep Multi-View Clustering: A Novel Attack and Defense Framework
  Haonan Huang (Guangdong University of Technology / RIKEN AIP)
  Guoxu Zhou (Guangdong University of Technology)
  Yanghang Zheng (Guangdong University of Technology)
  Yuning Qiu (RIKEN AIP)
  Andong Wang (RIKEN AIP)
  Qibin Zhao (RIKEN AIP)
• A General Framework for Learning from Weak Supervision
  Hao Chen (Carnegie Mellon University)
  Jindong Wang (Microsoft Research)
  Lei Feng (Nanyang Technological University)
  Xiang Li (Carnegie Mellon University)
  Yidong Wang (Peking University)
  Xing Xie (Microsoft Research)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Rita Singh (Carnegie Mellon University)
  Bhiksha Raj (Carnegie Mellon University)
• Balancing Similarity and Complementarity for Unimodal and Multimodal Federated Learning
  Kunda Yan (Tsinghua University)
  Sen Cui (Tsinghua University)
  Abudukelimu Wuerkaixi (Tsinghua University)
  Jingfeng Zhang (The University of Auckland)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Changshui Zhang (Tsinghua University)
• Causal Representation Learning Made Identifiable by Grouping of Observational Variables
  Hiroshi Morioka (RIKEN AIP)
  Aapo Hyvärinen (University of Helsinki / RIKEN AIP)
• Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
  Ming-Kun Xie (Nanjing University of Aeronautics and Astronautics)
  Jia-Hao Xiao (Nanjing University of Aeronautics and Astronautics)
  Pei Peng (Nanjing University of Aeronautics and Astronautics)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Sheng-Jun Huang (Nanjing University of Aeronautics and Astronautics)
• Discovering Multiple Solutions in Offline Reinforcement Learning
  Takayuki Osa (The University of Tokyo / RIKEN AIP)
  Tatsuya Harada (The University of Tokyo / RIKEN AIP)
• Diffusion Models Demand Contrastive Guidance for Adversarial Purification to Advance
  Mingyuan Bai* (RIKEN AIP)
  Wei Huang* (RIKEN AIP)
  Tenghui Li* (Guangdong University of Technology / RIKEN AIP)
  Andong Wang (RIKEN AIP)
  Junbin Gao (The University of Sydney)
  Cesar F Caiafa (CONICET)
  Qibin Zhao (RIKEN AIP)
  * Equal contribution
• Discovering More Effective Tensor Network Structure Search Algorithms via Large
  Language Models (LLMs)
  Junhua Zeng* (Guangdong University of Technology)
  Guoxu Zhou (Guangdong University of Technology)
  Chao Li (RIKEN AIP)
  Zhun Sun (Tencent Inc.)
  Qibin Zhao (RIKEN AIP)
  * The work was done when he was an intern at RIKEN AIP.
• Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation
  Yu-Yang Qian (Nanjing University)
  Peng Zhao (Nanjing University)
  Yu-Jie Zhang (The University of Tokyo)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Zhi-Hua Zhou (Nanjing University)
• Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
  Taira Tsuchiya (The University of Tokyo / RIKEN AIP)
  Shinji Ito (NEC / RIKEN AIP)
  Junya Honda (Kyoto University / RIKEN AIP)
• Generating Chain-of-Thoughts with a Direct Pairwise-Comparison Approach to Find the Most Promising Intermediate Thought
  Zhen-Yu Zhang (RIKEN AIP)
  Siwei Han (Fudan University)
  Huaxiu Yao (University of North Carolina at Chapel Hill)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Generalization Analysis of Stochastic Weight Averaging with General Sampling
  Peng Wang (Huazhong University of Science and Technology)
  Li Shen (Sun Yat-sen University)
  Zerui Tao (Tokyo University of Agriculture and Technology / RIKEN AIP)
  Shuaida He (Southern University of Science and Technology)
  Dacheng Tao (Nanyang Technological University)
• Generalized Sobolev Transport for Probability Measures on a Graph
  Tam Le* (The Institute of Statistical Mathematics (ISM) / RIKEN AIP)
  Truyen Nguyen* (The University of Akron)
  Kenji Fukumizu (The Institute of Statistical Mathematics (ISM))
  *equal contribution
• High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
  Yihang Chen (EPFL)
  Fanghui Liu (University of Warwick)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Volkan Cevher (EPFL)
• How do Transformers Perform In-Context Autoregressive Learning?
  Michael Eli Sander (Ecole Normale Supérieure)
  Raja Giryes (Tel Aviv University)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Mathieu Blondel (Google)
  Gabriel Peyré (Ecole Normale Supérieure)
• Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
  Jiacheng Zhang (University of Melbourne)
  Feng Liu (University of Melbourne)
  Dawei Zhou (Xidian University)
  Jingfeng Zhang (University of Auckland/RIKEN)
  Tongliang Liu (University of Sydney)
• Jacobian Regularizer-based Neural Granger Causality
  Wanqi Zhou (Xi’an Jiaotong University / RIKEN AIP)
  Shuanghao Bai (Xi’an Jiaotong University)
  Shujian Yu (Vrije Universiteit Amsterdam / UiT-The Arctic University of Norway)
  Qibin Zhao (RIKEN AIP)
  Badong Chen (Xi’an Jiaotong University)
• Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
  Wei Wang (The University of Tokyo / RIKEN AIP)
  Takashi Ishida (RIKEN AIP / The University of Tokyo)
  Yu-Jie Zhang (The University of Tokyo)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
  Shokichi Takakura (The University of Tokyo / RIKEN AIP / LY Corporation)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning
  Kakei Yamamoto (Massachusetts Institute of Technology)
  Kazusato Oko (The University of Tokyo / RIKEN AIP)
  Zhuoran Yang (Yale University)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• Mechanistic Design and Scaling of Hybrid Architectures
  Michael Poli (Together AI)
  Armin W Thomas (Stanford University)
  Eric Nguyen (Stanford University)
  Stefano Massaroli (RIKEN AIP / Liquid AI)
  Pragaash Ponnusamy (Together AI)
  Björn Deiseroth (Hessian AI)
  Kristian Kersting (Hessian AI)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Brian Hie (Stanford University / Arc Institute)
  Stefano Ermon (Stanford University / CZ Biohub)
  Christopher Ré (Stanford University)
  Ce Zhang (Together AI)
• Online Learning in Betting Markets: Profit versus Prediction
  Haiqing Zhu (Australian National University)
  Alexander Soen (Australian National University / RIKEN AIP)
  Yun Kuen Cheung (Australian National University)
  Lexing Xie (Australian National University)
• Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds
  Shion Takeno (Nagoya University / RIKEN AIP)
  Yu Inatsu (Nagoya Institute of Technology)
  Masayuki Karasuyama (Nagoya Institute of Technology)
  Ichiro Takeuchi (Nagoya University / RIKEN AIP)
• Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
  Dake Bu (City University of Hong Kong)
  Wei Huang (RIKEN AIP)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Ji Cheng (City University of Hong Kong)
  Qingfu Zhang (City University of Hong Kong)
  Zhiqiang Xu (Mohamed bin Zayed University of Artificial Intelligence)
  Hau-San Wong (City University of Hong Kong)
• Riemannian coordinate descent algorithms on matrix manifolds.
  Andi Han (Riken AIP)
  Pratik Jawanpuria (Microsoft India).
  Bamdev Mishra (Microsoft India)
• Self-attention Networks Localize When QK-eigenspectrum Concentrates
  Han Bao(Kyoto University)
  Ryuichiro Hataya(RIKEN AIP)
  Ryo Karakida(AIST)
• SILVER: Single-loop variance reduction and application to federated learning
  Kazusato Oko (The University of Tokyo / RIKEN AIP)
  Shunta Akiyama (CyberAgent, Inc. / The University of Tokyo)
  Denny Wu (New York University / Flatiron Institute)
  Tomoya Murata (NTT DATA Mathematical Systems Inc. / RIKEN AIP)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning
  Matthias Weissenbacher (RIKEN AIP)
  Rishabh Agarwal (Google Research)
  Yoshinobu Kawahara (Osaka University / RIKEN AIP)
• Sliced Wasserstein with Random-Path Projecting Directions
  Khai Nguyen (The University of Texas, Austin)
  Shujian Zhang (The University of Texas, Austin)
  Tam Le (The Institute of Statistical Mathematics (ISM) / RIKEN AIP)
  Nhat Ho (The University of Texas, Austin)
• State-Free Inference of State-Space Models: The *Transfer Function* Approach
  Rom Parnichkun (The University of Tokyo)
  Stefano Massaroli (RIKE AIP / Liquid AI)
  Alessandro Moro (RITECS Inc.)
  Michael Poli (Together AI)
  Jimmy T.H. Smith (Stanford University)
  Ramin Hasani (Massachusetts Institute of Technology)
  Mathias Lechner (Massachusetts Institute of Technology / Liquid AI)
  Qi An (The University of Tokyo)
  Christopher Re (Stanford University)
  Hajime Asama (The University of Tokyo)
  Stefano Ermon (Stanford University / CZ Biohub)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Atsushi Yamashita (The University of Tokyo)
• Statistical Test for Attention Maps in Vision Transformers
  Tomohiro Shiraishi (Nagoya University)
  Daiki Miwa (Nagoya Institute of Technology)
  Teruyuki Katsuoka (Nagoya University)
  Vo Nguyen Le Duy (Vietnam National University / RIKEN AIP)
  Kouichi Taji (Nagoya University)
  Ichiro Takeuchi (Nagoya University / RIKEN AIP)
• Understanding Diffusion Models by Feynman’s Path Integral
  Yuji Hirono (Kyoto University)
  Akinori Tanaka (RIKEN AIP/RIKEN iTHEMS/Keio University)
  Kenji Fukushima (The University of Tokyo)
• Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI
  Theodore Papamarkou (The University of Manchester)
  Maria Skoularidou (Eric and Wendy Schmidt Center / Broad Institute of MIT and Harvard)
  Konstantina Pall (Spotify)
  Laurence Aitchison (University of Bristol)
  Julyan Arbel (Centre Inria de l’Universite Grenoble Alpes)
  David Dunson (Duke University)
  Maurizio Filippone (KAUST)
  Vincent Fortuin (Helmholtz AI / Technical University of Munich)
  Philipp Hennig (University of Tubingen)
  Jose Miguel Hernandez Lobato (University of Cambridge)
  Aliaksandr Hubin (University of Oslo)
  Alexander Immer (Max Planck ETH)
  Theofanis Karaletsos (Pyramidal, Inc.)
  Mohammad Emtiyaz Khan (RIKEN AIP)
  Agustinus Kristiadi (Vector Institute)
  Yingzhen Li (Imperial College London)
  Stephan Mandt (UC Irvine)
  Christopher Nemeth (Lancaster University)
  Michael A. Osborne (University of Oxford)
  Tim G. J. Rudner (New York University)
  David Rugamer (LMU Munich and MCML)
  Yee Whye The (DeepMind / University of Oxford)
  Max Welling (University of Amsterdam)
  Andrew Gordon Wilson (New York University)
  Ruqi Zhang (Purdue University)
• Position Paper: C*-Algebraic Machine Learning: Moving in a New Direction
  Yuka Hashimoto (NTT / RIKEN AIP)
  Masahiro Ikeda (RIKEN AIP / Keio University)
  Hachem Kadri (Aix-Marseille University)

関連研究室