Center for Advanced Intelligence Project

Update: January 31, 2022

12 papers were accepted at ICLR 2022, a major conference on machine learning. For more details, please refer to the link below.

[Accepted Papers] https://openreview.net/group?id=ICLR.cc/2022/Conference

[Oral Presentation]

• PiCO: Contrastive Label Disambiguation for Partial Label Learning
  Haobo Wang (Zhejiang University)
  Ruixuan Xiao (Zhejiang University)
  Yixuan Li (University of Wisconsin, Madison)
  Lei Feng (Chongqing University / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Gang Chen (Zhejiang University)
  Junbo Zhao (Zhejiang University)
  https://openreview.net/forum?id=EhYjZy6e1gJ

[Spotlight Presentation]

• Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness
  Sho Okumoto (The University of Tokyo)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  https://openreview.net/forum?id=dgxFTxuJ50e
• Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
  Haoang Chi (National University of Defense Technology)
  Feng Liu (University of Technology Sydney)
  Wenjing Yang (National University of Defense Technology)
  Long Lan (National University of Defense Technology)
  Tongliang Liu (University of Sydney / RIKEN AIP)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Mingyuan Zhou (The University of Texas at Austin)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  https://openreview.net/forum?id=MEpKGLsY8f

[Poster Presentation]

• Adversarial Robustness Through the Lens of Causality
  Yonggang Zhang (University of Science and Technology of China / Hong Kong Baptist University)
  Mingming Gong (University of Melbourne)
  Tongliang Liu (University of Sydney / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Xinmei Tian (University of Science and Technology of China)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Bernhard Schölkopf (Max Planck Institute for Intelligent Systems)
  Kun Zhang (Carnegie Mellon University)
  https://openreview.net/forum?id=cZAi1yWpiXQ
• Exploiting Class Activation Value for Partial-Label Learning
  Fei Zhang (Shanghai Jiao Tong University)
  Lei Feng (Chongqing University / RIKEN AIP)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Tongliang Liu (University of Sydney / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Tao Qin (Microsoft Research Asia)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  https://openreview.net/forum?id=qqdXHUGec9h
• Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
  Nan Lu (The University of Tokyo)
  Zhao Wang (The Chinese University of Hong Kong)
  Xiaoxiao Li (University of British Columbia)
  Gang Niu (RIKEN AIP)
  Qi Dou (The Chinese University of Hong Kong)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  https://openreview.net/forum?id=WHA8009laxu
• Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
  Jiaheng Wei (University of California, Santa Cruz)
  Zhaowei Zhu (University of California, Santa Cruz)
  Hao Cheng (University of California, Santa Cruz)
  Tongliang Liu (University of Sydney / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Yang Liu (University of California, Santa Cruz)
  https://openreview.net/forum?id=TBWA6PLJZQm
• Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization
  Kazusato Oko (The University of Tokyo)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Atsushi Nitanda (Kyushu Institute of Technology / RIKEN AIP / JST PRESTO)
  Denny Wu + (University of Toronto / Vector Institute)
  https://openreview.net/forum?id=PQQp7AJwz3
• Reliable Adversarial Distillation with Unreliable Teachers
  Jianing Zhu (Hong Kong Baptist University)
  Jiangchao Yao (Alibaba Group)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Jingfeng Zhang (RIKEN AIP)
  Tongliang Liu (University of Sydney / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Jingren Zhou (Alibaba Group)
  Jianliang Xu (Hong Kong Baptist University)
  Hongxia Yang (Alibaba Group)
  https://openreview.net/forum?id=u6TRGdzhfip
• Rethinking Class-Prior Estimation for Positive-Unlabeled Learning
  Yu Yao (University of Sydney)
  Tongliang Liu (University of Sydney / RIKEN AIP)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Mingming Gong (University of Melbourne)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Dacheng Tao (JD.com)
  https://openreview.net/forum?id=aYAA-XHKyk
• Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
  Xiaobo Xia (University of Sydney)
  Tongliang Liu (University of Sydney / RIKEN AIP)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Mingming Gong (University of Melbourne)
  Jun Yu (University of Science and Technology of China)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  https://openreview.net/forum?id=xENf4QUL4LW
• Understanding the Variance Collapse of SVGD in High Dimensions
  Jimmy Ba (University of Toronto / Vector Institute)
  Murat A Erdogdu (University of Toronto / Vector Institute)
  Marzyeh Ghassemi (Massachusetts Institute of Technology)
  Shengyang Sun (University of Toronto)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Denny Wu + (University of Toronto / Vector Institute)
  Tianzong Zhang (Tsinghua University)
  https://openreview.net/forum?id=Qycd9j5Qp9J

+Past interns of RIKEN AIP

Related Laboratories