Wenshui Luo (罗文水)
Biography
I am currently a Ph.D. Student at the School of Automation and Perception, Shanghai Jiao Tong University, supervised by Prof. Chen Gong. Before this, I received my master's degree in Nanjing University of Science and Technology. Meanwhile, I participated in the remote internship program of Prof. Masashi Sugiyama at the RIKEN AIP from Oct. 2022 to Oct. 2023, under the guidance of Gang Niu and Shuo Chen.
During my master's studies, I focused on the problem of weakly supervised machine learning, with particular emphasis on the problem of Label Noise Learning (LNL). Moreover, I am interested in Learning under Distribution Drift, and Continual Learning, based on which I hope to build robust, reliable, and trustworthy systems. Over the past few years, I have received many awards, including National Scholarship, Huawei Scholarship, the first prices of some national mathematics competitions and mathematical modeling competitions, and the outstanding master's thesis award of the Jiangsu Province Artificial Intelligence Society (JSAI).
Research Interests
- Weakly Supervised Learning, such as learning from incorrect, inaccurate, insufficient supervision. Especially, learning from noisy labels.
- Continual Learning, such as task-free online continual learning.
- Learning from Non-stationary Data Streams, such as online learning from non-stationary streams.
- Reinforcement Learning with Verifiable Rewards, specifically in multi-task learning.
Education
Work & Internship Experience
-
2024.06~2026.03: Program Leader, Continual Learning Project of Financial Fraud Detection, Ant Group, Shanghai, China.
-
2022.10~2023.10: Research Intern, Imperfect Information Learning Team, RIKEN center for Advanced Intelligence Project (AIP), Tokyo, Japan. Supervised by Prof. Masashi Sugiyama, Gang Niu and Shuo Chen.
Publications
-
Continual Fraud Detection with Dynamic Feature Space.
Wenshui Luo*, Kerun Mi*, etc.
ACM SIGKDD, 2026.
-
A Theoretical Perspective on Streaming Noisy Data with Distribution Shift.
Wenshui Luo, Shuo chen, Tao Zhou, Chen Gong.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2025.
-
Estimating Per-Class Statistics for Label Noise Learning.
Wenshui Luo, Shuo Chen, Tongliang Liu, Bo Han, Gang Niu, Masashi Sugiyama, Dacheng Tao, Chen Gong.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024.
-
Rank Aggregation in Crowdsourcing for Listwise Annotations.
Wenshui Luo*, Haoyu Liu*, Yongliang Ding*, T. Zhou, S. Wan, R. Wu, M. Lin, C. Zhang, C. Fan, C. Gong.
arXiv preprint, 2024.
Patents
-
A Classification Method for Images with Noisy Annotations, CN118506069B, 2025.
Wenshui Luo, Chen Gong, Yalei Shao, Wanyin Wu, ChongChong Qi, Xu Lin.
Honors and Awards
- Outstanding Master's Thesis Award of the Jiangsu Province Artificial Intelligence Society, 2025.
- National Scholarship, 2024.
- Huawei Scholarship, 2022.
- Outstanding graduates majored in science and engineering of Nanjing University of Science and Technology (NJUST), 2022.
- Final of 11th National Mathematics Competition for College Student, First Prize, 2021.
rank 42/140176 nationwide.
- National Mathematical Modeling Contest for Undergraduate Students, First Prize, 2021.
Annual Selection Rate < 0.7%.
- 11th National Mathematics Competition for College Student (Jiangsu Division), First Prize, 2020.
rank 14/7518, shortlisted for the national final, with a total of 300 people nationwide shortlisted.
- 16th Advanced Mathematics Competition of Jiangsu Province, China First Prize, 2020.
rank 3/14942.
Academic Services
-
Conference Reviewer: ICML, CVPR, SIGKDD, CIKM, AISTATS, IEEE CAI, etc.