A Unified Solution to Diverse Heterogeneities in One-Shot Federated Learning

Files

hdl_149547.pdf (10.17 MB)
  (Published version)

Date

2025

Authors

Bai, J.
Song, Y.
Wu, D.
Sajjanhar, A.
Xiang, Y.
Zhou, W.
Tao, X.
Li, Y.
Li, Y.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '25), 2025, vol.2, pp.71-82

Statement of Responsibility

Jun Bai, Yiliao Song, Di Wu, Atul Sajjanhar, Yong Xiang, Wei Zhou, Xiaohui Tao, Yan Li, Yue Li

Conference Name

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (3 Aug 2025 - 4 Aug 2025 : Toronto, ON, Canada)

Abstract

One-Shot Federated Learning (OSFL) restricts communication between the server and clients to a single round, significantly reducing communication costs and minimizing privacy leakage risks compared to traditional Federated Learning (FL), which requires multiple rounds of communication. However, existing OSFL frameworks remain vulnerable to distributional heterogeneity, as they primarily focus on model heterogeneity while neglecting data heterogeneity. To bridge this gap, we propose FedHydra, a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity. Unlike existing OSFL approaches, FedHydra introduces a novel two-stage learning mechanism. Specifically, it incorporates model stratification and heterogeneity-aware stratified aggregation to mitigate the challenges posed by both model and data heterogeneity. By this design, the data and model heterogeneity issues are simultaneously monitored from different aspects during learning. Consequently, FedHydra can effectively mitigate both issues by minimizing their inherent conflicts. We compared FedHydra with five SOTA baselines on four benchmark datasets. Experimental results show that our method outperforms the previous OSFL methods in both homogeneous and heterogeneous settings. The code is available at https://github.com/Jun-B0518/FedHydra.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2025 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution 4.0 International License.

License

Call number

Persistent link to this record