About Me
I earned my Ph.D. degree in Computer Science at UC San Diego, co-advised by Prof. Rajesh K. Gupta and Prof. Jingbo Shang. Prior to UCSD, I completed my B.S. (with honors) in Computer Science at Fudan University.
My research focuses on developing robust machine learning systems in resource-constrained and heterogeneous environments. My primary areas of interest include:
- Fast model adaptation under distribution shift
- Machine learning in data-scarce systems
- Federated learning in heterogeneous distributed environments
These research directions have various applications such as anomaly detection, human activity recognition, health analytics, etc.
Selected Publications
-
Orthogonal Calibration for Asynchronous Federated Learning.
Jiayun Zhang, Shuheng Li, Haiyu Huang, Xiaofan Yu, Rajesh K. Gupta, Jingbo Shang
Preprint. arXiv:2502.15940
-
Matching Skeleton-based Activity Representations with Heterogeneous Signals for HAR.
Shuheng Li, Jiayun Zhang, Xiaohan Fu, Xiyuan Zhang, Jingbo Shang, Rajesh K. Gupta.
ACM Conference on Embedded Networked Sensor Systems (SenSys), 2025.
-
REACT: Residual-Adaptive Contextual Tuning for Fast Model Adaptation in Threat Detection.
Jiayun Zhang, Junshen Xu, Bugra Can, Yi Fan.
The Web Conference (WWW), 2025.
Also presented at Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability at NeurIPS, 2024.
-
Contextual Inference From Sparse Shopping Transactions Based on Motif Patterns.
Jiayun Zhang, Xinyang Zhang, Dezhi Hong, Rajesh K. Gupta, and Jingbo Shang.
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025.
-
Learn from Failure: Fine-tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
Chenyang An, Zhibo Chen, Qihao Ye, Emily First, Letian Peng, Jiayun Zhang, Zihan Wang, Sorin Lerner, Jingbo Shang.
Annual Meeting of the Association for Computational Linguistics (ACL), 2024.
-
How Few Davids Improve One Goliath: Federated Learning in Resource-Skewed Edge Computing Environments.
Jiayun Zhang, Shuheng Li, Haiyu Huang, Zihan Wang, Xiaohan Fu, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang.
The Web Conference (WWW), 2024. (selected as oral)
-
Physics-Informed Data Denoising for Real-Life Sensing Systems.
Xiyuan Zhang, Xiaohan Fu, Diyan Teng, Chengyu Dong, Keerthivasan Vijayakumar, Jiayun Zhang, Ranak Roy Chowdhury, Junsheng Han, Dezhi Hong, Rashmi Kulkarni, Jingbo Shang and Rajesh K. Gupta.
ACM Conference on Embedded Networked Sensor Systems (SenSys), 2023.
-
Unleashing the Power of Shared Label Structures for Human Activity Recognition.
Xiyuan Zhang, Ranak Roy Chowdhury, Jiayun Zhang, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang.
ACM International Conference on Information and Knowledge Management (CIKM), 2023.
-
Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Framework.
Jiayun Zhang, Xiyuan Zhang, Xinyang Zhang, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang.
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023.
-
Minimally Supervised Contextual Inference from Human Mobility: An Iterative Collaborative Distillation Framework.
Jiayun Zhang, Xinyang Zhang, Dezhi Hong, Rajesh K. Gupta, and Jingbo Shang.
International Joint Conferences on Artificial Intelligence (IJCAI), 2023.
Work Experience
-
Amazon Web Service
Applied Scientist Intern in Security Analytics and AI Research (SAAR) Team. Jun – Sep 2024
Work on fast model adaptation under distribution shift in threat detection.
-
VMware
MTS (Member of Technical Staff) Intern. Apr – Oct 2018
Worked on ML-based log analysis system for automatic program failure detection in internal bug reporting platform.
Professional Services
- Conference Program Committee Member / Reviewer: KDD'25/23, WWW'25/24, SDM'24, AAAI'24/23, UbiComp'23.
- Journal Reviewer: Computer Communications, IEEE Internet of Things Journal.