张豪

2019年9月-2025年9月 上海交通大学（信息智能研究所） 信息与通信工程专业 博士

2015年9月-2019年6月 电子科技大学（通信与信息工程学院） 通信工程 学士

2025年12月- 华东师范大学 通信与电子工程学院 紫江青年学者

张豪，现为华东师范大学紫江青年学者。分别于2019年和2025年在电子科技大学和上海交通大学获得学士学位和工学博士学位。主要研究方向为联邦学习、分布式优化、分布式大模型后训练、信息瓶颈与贝叶斯学习等。当前的研究重点是面向大模型边云协同训练场景，构建分布式学习收敛速率与泛化误差的理论框架，系统揭示数据异构性与隐私约束对最优误差界的影响机理。

Federated learning, Distributed optimization, Bayesian Learning, Distributed LLM fine-tuning

1. Hao Zhang, Chenglin Li, Wenrui Dai, Ziyang Zheng, Junni Zou, Hongkai Xiong, “Stabilizing and Accelerating Federated Learning on Heterogeneous Data with Partial Client Participation”, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), vol. 47, no. 1, pp. 67-83, Jan. 2025. (CCF-A)

2. Hao Zhang, Chenglin Li, Wenrui Dai, Junni Zou, Hongkai Xiong, “Federated Learning Based on Model Discrepancy and Variance Reduction”, IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), vol. 36, no. 6, pp. 10407-10421, June 2025.

3. Hao Zhang, Chenglin Li, Nuowen Kan, Ziyang Zheng, Wenrui Dai, Junni Zou, Hongkai Xiong, “Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach”, Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024), Dec. 2024. (CCF-A)

4. Hao Zhang, Chenglin Li, Wenrui Dai, Junni Zou, Hongkai Xiong, “FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization”, International Conference on Machine Learning (ICML 2023), July 2023. (CCF-A) 

5. Li Ding*, Hao Zhang*, Wenrui Dai, Chenglin Li, Weijia Lu, Zhifei Yang, Xiaodong Zhang, Xiaofeng Ma, Junni Zou, Hongkai Xiong, “LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation”, International Conference on Machine Learning (ICML 2025), July 2025. (CCF-A) (共一)

6. Xinyi Lu*, Hao Zhang*, Chenglin Li, Weijia Lu, Zhifei Yang, Wenrui Dai, Xiaodong Zhang, Xiaofeng Ma, Can Zhang, Junni Zou, Hongkai Xiong, “FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates”, International Conference on Machine Learning (ICML 2025), July 2025. (CCF-A) (共一)