Hao Zhang
Portrait

I am a Ph.D. candidate under the supervision of Chenglin Li and Hongkai Xiong at the MIN Laboratory.

My research interests include Federated Learning, Distributed Compression and Optimization, Bayesian Learning, and the Information Bottleneck.

Google Scholar GitHub
#
Education
  • Shanghai Jiao Tong University
    Shanghai Jiao Tong University
    Department of Electronic Engineering
    Ph.D. Student
    Sep. 2019 - present
  • University of Electronic Science and Technology of China
    University of Electronic Science and Technology of China
    Department of Electronic Engineering
    B.S.
    Sep. 2015 - Jul. 2019
News
2024
The paper titled: "Federated Learning Based on Model Discrepancy and Variance Reduction" has been accepted by the journal TNNLS.
Dec 20
The paper title: "FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates" has been submitted to ICLR 2025 and is under review.
Oct 03
The paper titled: "Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach" has been accepted by the conference NeurIPS 2024.
Sep 26
The paper titled: "Stabilizing and Accelerating Federated Learning on Heterogeneous Data with Partial Client Participation" has been accepted by the journal TPAMI.
Sep 19
2023
The paper titled: 'FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization' has been accepted by the conference ICML 2023.
Apr 30
Selected Publications (view all )
Federated Learning Based on Model Discrepancy and Variance Reduction
Federated Learning Based on Model Discrepancy and Variance Reduction

Hao Zhang, Chenglin Li, Wenrui Dai, Ziyang Zheng, Junni Zou, Hongkai Xiong

IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2024

[Code] [Paper]

Federated Learning Based on Model Discrepancy and Variance Reduction

Hao Zhang, Chenglin Li, Wenrui Dai, Ziyang Zheng, Junni Zou, Hongkai Xiong

IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2024

[Code] [Paper]

Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach
Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach

Hao Zhang, Chenglin Li, Nuowen Kan, Ziyang Zheng, Wenrui Dai, Junni Zou, Hongkai Xiong

Neural Information Processing Systems (NeurIPS) 2024

[Code] [Paper]

Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach

Hao Zhang, Chenglin Li, Nuowen Kan, Ziyang Zheng, Wenrui Dai, Junni Zou, Hongkai Xiong

Neural Information Processing Systems (NeurIPS) 2024

[Code] [Paper]

Stabilizing and Accelerating Federated Learning on Heterogeneous Data with Partial Client Participation
Stabilizing and Accelerating Federated Learning on Heterogeneous Data with Partial Client Participation

Hao Zhang, Chenglin Li, Wenrui Dai, Ziyang Zheng, Junni Zou, Hongkai Xiong

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2024

[Code] [Paper]

Stabilizing and Accelerating Federated Learning on Heterogeneous Data with Partial Client Participation

Hao Zhang, Chenglin Li, Wenrui Dai, Ziyang Zheng, Junni Zou, Hongkai Xiong

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2024

[Code] [Paper]

FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization
FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization

Hao Zhang, Chenglin Li, Wenrui Dai, Junni Zou, Hongkai Xiong

International Conference on Machine Learning (ICML) 2023

[Code] [Paper]

FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization

Hao Zhang, Chenglin Li, Wenrui Dai, Junni Zou, Hongkai Xiong

International Conference on Machine Learning (ICML) 2023

[Code] [Paper]

All publications