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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Jun, Song, Yiliao, Wu, Di, Sajjanhar, Atul, Xiang, Yong, Zhou, Wei, Tao, Xiaohui, Li, Yan, Li, Yue
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912407173988352
author Bai, Jun
Song, Yiliao
Wu, Di
Sajjanhar, Atul
Xiang, Yong
Zhou, Wei
Tao, Xiaohui
Li, Yan
Li, Yue
author_facet Bai, Jun
Song, Yiliao
Wu, Di
Sajjanhar, Atul
Xiang, Yong
Zhou, Wei
Tao, Xiaohui
Li, Yan
Li, Yue
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21119
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
Bai, Jun
Song, Yiliao
Wu, Di
Sajjanhar, Atul
Xiang, Yong
Zhou, Wei
Tao, Xiaohui
Li, Yan
Li, Yue
Distributed, Parallel, and Cluster Computing
Machine Learning
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.
title A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
topic Distributed, Parallel, and Cluster Computing
Machine Learning
url https://arxiv.org/abs/2410.21119