FedAlign: Differentially Private Distribution Alignment for Non-IID Federated Learning

Peng Wu; Jiapeng Zhang; Yingjie Song; Xiong Xiao; Zhuo Tang

CVPR 20260 citations

FedAlign: Differentially Private Distribution Alignment for Non-IID Federated Learning

Peng Wu, Jiapeng Zhang, Yingjie Song, Xiong Xiao, Zhuo Tang

Abstract

Federated Learning (FL) enables collaborative model training without sharing raw data, but client data are often Non-Independent and Identically Distributed (Non-IID), which often slow convergence and degrade global performance. Meanwhile, privacy preservation is also a critical concern in FL. To address these two issues, we propose FedAlign, a differentially private framework that aligns local data distributions via client-side statistical moment alignment. Clients upload perturbed distribution statistics, which the server aggregates to infer global distribution characteristics and guide local alignment, thereby reducing inter-client discrepancies. Experiments and theoretical analysis show that FedAlign accelerates convergence and improves accuracy under Non-IID settings while preserving rigorous privacy guarantees.

BibTeX

@inproceedings{cvpr2026_fedaligndifferen,
  title = {FedAlign: Differentially Private Distribution Alignment for Non-IID Federated Learning},
  author = {Peng Wu and Jiapeng Zhang and Yingjie Song and Xiong Xiao and Zhuo Tang},
  booktitle = {CVPR 2026},
  year = {2026}
}