RIKEN Center for Advanced Intelligence Project Imperfect Information Learning Team
Team Director: Masashi Sugiyama (D.Eng.)
Research Summary
Recently, machine learning technology with big data has been actively investigated and its effectiveness has been demonstrated. However, depending on application domains, it is difficult or even it is not possible to collect a large amount of data. In the Imperfect Information Learning Team, for various machine learning tasks including supervised learning, unsupervised learning, and reinforcement learning, we develop novel algorithms that allow accurate learning from limited information. We also elucidate their theoretical properties and apply them to various real-world applications ranging from fundamental science to business.
Research Subjects:
- Development of machine learning algorithms from imperfect information
- Theoretical analysis of machine learning algorithms
- Real-world application of machine learning algorithms
Main Research Fields
- Informatics
Related Research Fields
- Intelligent informatics
- Perceptual information processing
- Statistical science
Keywords
- artificial intelligence
- machine learning
- weakly supervised learning
- reinforcement learning
- deep learning
Selected Publications
- 1.
Zhang, Z.-Y., Xie, Z., Yao, H., & Sugiyama, M.:
"Test-time adaptation in non-stationary environments via adaptive representation alignment."
Neural Information Processing Systems (NeurIPS2024), to appear. - 2.
Zhang, Y. & Sugiyama, M.:
"Enriching disentanglement: From logical definitions to quantitative metrics."
Neural Information Processing Systems (NeurIPS2024), to appear. - 3.
Wang, W., Ishida, T., Zhang, Y.-J., Niu, G., & Sugiyama, M.:
"Learning with complementary labels revisited: The selected-completely-at-random setting is more practical."
International Conference on Machine Learning (ICML2024), pp. 50683-50710, 2024. - 4.
Zhang, Z.-Y., Han, S., Yao, H., Niu, G., & Sugiyama, M.:
"Generating chain-of-thoughts with a direct pairwise-comparison approach to find the most promising intermediate thought."
International Conference on Machine Learning (ICML2024), pp. 58967-58983, 2024. - 5.
Chen, S., Niu, G., Gong, C., Koc, O., Yang, J., & Sugiyama, M.:
"Robust similarity learning with difference alignment regularization."
International Conference on Learning Representations (ICLR2024), 22 pages, 2024. - 6.
Wang, W., Feng, L., Jiang, Y., Niu, G., Zhang, M.-L., & Sugiyama, M.:
"Binary classification with confidence difference."
Neural Information Processing Systems (NeurIPS2023), pp. 5936-5960, 2023. - 7.
Zhang, Y. & Sugiyama, M.:
"A category-theoretical meta-analysis of definitions of disentanglement."
International Conference on Machine Learning (ICML2023), pp. 41596-41612, 2023. - 8.
Ishida, T., Yamane, I., Charoenphakdee, N., Niu, G., & Sugiyama, M.:
"Is the performance of my deep network too good to be true? A direct approach to estimating the Bayes error in binary classification."
International Conference on Learning Representations (ICLR2023), 22 pages, 2023. - 9.
Chen, S., Gong, C., Li, J., Yang, J., Niu, G., & Sugiyama, M.:
"Learning contrastive embedding in low-dimensional space."
Neural Information Processing Systems (NeurIPS2022), pp. 6345-6357, 2022. - 10.
Sugiyama, M., Bao, H., Ishida, T., Lu, N., Sakai, T., & Niu, G.:
"Machine Learning from Weak Supervision: An Empirical Risk Minimization Approach,"
320 pages, MIT Press, Cambridge, Massachusetts, USA, 2022.
Recent Research Results
Nov. 26, 2018
Smarter AI: machine learning without negative data
Related Links
Lab Members
Principal investigator
- Masashi Sugiyama
- Team Director
Core members
- Gang Niu
- Senior Research Scientist
- Takashi Ishida
- Research Scientist
- Zhen-Yu Zhang
- Postdoctoral Researcher
- Okan Koc
- Postdoctoral Researcher
- Ming-Kun Xie
- Postdoctoral Researcher
- Xinqiang Cai
- Postdoctoral Researcher
- Yu-Jie Zhang
- Postdoctoral Researcher
- Shinichi Nakajima
- Senior Visiting Scientist
- Shuo Chen
- Visiting Scientist
- Florian Baptiste Yger
- Visiting Scientist
- Miao Xu
- Visiting Scientist
- Bo Han
- Visiting Scientist
- Feng Liu
- Visiting Scientist
- Tongliang Liu
- Visiting Scientist
- Nan Lu
- Visiting Scientist
- Tingting Zhao
- Visiting Scientist
- Jingfeng Zhang
- Visiting Scientist
- Peng Zhao
- Visiting Scientist
- Lei Feng
- Visiting Scientist
- Motoya Ohnishi
- Visiting Scientist
- Salah Ghamizi
- Visiting Scientist
- Alexander Soen
- Student Trainee
- Zhikang Chen
- Student Trainee
- Xue Jiang
- Student Trainee
- Jingwen Fu
- Intern
- Yuting Tang
- Junior Research Associate
- Wei Wang
- Junior Research Associate
- Ryota Ushio
- Junior Research Associate
- DongDong Wu
- Junior Research Associate
Contact Information
Nihonbashi 1-chome Mitsui Building, 15th floor,
1-4-1 Nihonbashi,
Chuo-ku, Tokyo
103-0027, Japan
Email: masashi.sugiyama [at] riken.jp