Publications

Working Papers

[W1] Zehan Zhu et al. DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication.

[W2] Yipeng Shen, Zehan Zhu et al. Bandwidth-Aware Network Topology Optimization for Efficient Parameter Synchronization in Decentralized Learning.

[W3] Wen Wen, Guangquan Xu, Zehan Zhu et al. Dynamic Participation Undermines Byzantine Robustness in Distributed Federated Learning: Vulnerability Analysis and a Cross-Round Verification Framework.

Published/Accepted Papers

[IJCAI’25] Zehan Zhu, Yan Huang, Xin Wang, Shouling Ji, and Jinming Xu. Dyn-D²P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee.
The 34th International Joint Conference on Artificial Intelligence. (CCF-A, Paper)

[IJCAI’24] Zehan Zhu, Yan Huang, Xin Wang, and Jinming Xu. PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds.
The 33rd International Joint Conference on Artificial Intelligence. (CCF-A, Paper)

[TSIPN’24] Zehan Zhu, Ye Tian, Yan Huang, Jinming Xu, and Shibo He. R-FAST: Robust Fully-Asynchronous Stochastic Gradient Tracking over General Topology.
IEEE Transactions on Signal and Information Processing over Networks. (Paper)

[JPDC’24] Changzhi Yan, Zehan Zhu, Youcheng Niu, Cong Wang, Cheng Zhuo, and Jinming Xu. PerfTop: Towards Performance Prediction of Distributed Learning over General Topology.
Journal of Parallel and Distributed Computing. (CCF-B, Paper)

[CDC’23] Zehan Zhu, Yan Huang, Chengcheng Zhao, and Jinming Xu. Asynchronous Byzantine-Robust Stochastic Aggregation with Variance Reduction for Distributed Learning.
The 62nd IEEE Conference on Decision and Control. (CAA-A, Paper)

[ICML’22] Yan Huang, Ying Sun, Zehan Zhu, Changzhi Yan, and Jinming Xu. Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology.
The 39th International Conference on Machine Learning. (CCF-A, Paper)