侍蒋鑫 Jiang-Xin Shi
Ph.D. Student Supervisor: Professor Yu-Feng Li Email: shijx@lamda.nju.edu.cn |
Currently, I am a first year Ph.D. student from School of Artificial Intelligence in Nanjing University. I am also a member of LAMDA Group, which is led by professor Zhi-Hua Zhou.
Before this, I received my B.Sc. degree from School of Computer Science, Northwestern Polytechnical University in July 2020. In the same year, I was admitted to study for a M.Sc. degree in Department of Computer Science and Technology, Nanjing University without entrance examination.
My research interests include Machine Learning and Data Mining.
Specifically, I am interested in Long-Tail Learning. Here is a repository maintained by Dr. Tong Wei: [Awesome Long-Tail Learning]
Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model.
Jiang-Xin Shi*, Chi Zhang*, Tong Wei, Yu-Feng Li.
In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024).
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts.
[code]
Jiang-Xin Shi*, Tong Wei*, Zhi Zhou, Jie-Jing Shao, Xin-Yan Han, Yu-Feng Li.
In Proceedings of the 41th International Conference on Machine Learning (ICML 2024).
DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection.
Zhi Zhou, Ming Yang, Jiang-Xin Shi, Lan-Zhe Guo, Yu-Feng Li.
In Proceedings of the 41th International Conference on Machine Learning (ICML 2024).
How Re-sampling Helps for Long-Tail Learning?
[pdf]
[code]
Jiang-Xin Shi*, Tong Wei*, Yuke Xiang, Yu-Feng Li.
In Advances in Neural Information Processing Systems 36 (NeurIPS 2023).
Prototypical Classifier for Robust Class-Imbalanced Learning.
[pdf]
[code]
Tong Wei*, Jiang-Xin Shi*, Yu-Feng Li, Min-Ling Zhang.
In Advances in Knowledge Discovery and Data Mining (PAKDD 2022).
(PAKDD 2022 Best Paper Award)
Probabilistic Label Tree for Streaming Multi-Label Learning.
[pdf]
[code]
Tong Wei*, Jiang-Xin Shi*, Yu-Feng Li.
In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2021).
Residual Diverse Ensemble for Long-Tailed Multi-Label Text Classification.
[pdf]
[code]
Jiang-Xin Shi*, Tong Wei*, Yu-Feng Li.
SCIENCE CHINA Information Sciences (SCIS), 2024.
Transfer and Share: Semi-Supervised Learning from Long-Tailed Data.
[pdf]
[code]
Tong Wei*, Qian-Yu Liu*, Jiang-Xin Shi, Wei-Wei Tu, Lan-Zhe Guo.
Machine Learning (MLJ), 2022.
Investigating the Limitation of CLIP Models: The Worst-Performing Categories.
[arxiv]
Jie-Jing Shao*, Jiang-Xin Shi*, Xiao-Wen Yang*, Lan-Zhe Guo, Yu-Feng Li.
arXiv:2310.03324, 2023.
A Survey on Extreme Multi-label Learning.
[arxiv]
Tong Wei, Zhen Mao, Jiang-Xin Shi, Yu-Feng Li, Min-Ling Zhang.
arXiv:2210.03968, 2022.
Robust Long-Tailed Learning under Label Noise.
[arxiv]
[code]
Tong Wei*, Jiang-Xin Shi*, Wei-Wei Tu, Yu-Feng Li.
arXiv:2108.11569, 2021.
南京大学博士生英才奖学金一等奖, 2023
PAKDD Best Paper Award, 2022
Outstanding Graduate of Northwestern Polytechnical University, 2020
CCF Elite Collegiate Award, 2019
ACM-ICPC Asia Regional Contest Gold Medal, 2018 and 2017
National Scholarship, 2018 and 2017
Reviewer for Conferences: ICML 2023, 2024; NeurIPS 2023, 2024; ICLR 2024; KDD 2024; AAAI 2023, 2024, ECAI 2023, ACML 2022.
Reviewer for Journal: Machine Learning.
Teaching Assistant for Introduction to Advanced Machine Learning, Nanjing Univeristy, Spring, 2022
Teaching Assistant for Introduction to Machine Learning, Nanjing Univeristy, Fall, 2021
Captain of Northwestern Polytechnical University ACM-ICPC Competition Team, 2018
Email: shijx@lamda.nju.edu.cn
Laboratory: Room 113, Computer Science Building, Nanjing University Xianlin Campus, Nanjing, China