Distributionally Robust Federated Learning: An ADMM Algorithm

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bai, Wen, Wong, Yi, Qiao, Xiao, Ho, Chin Pang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915211492982784
author Bai, Wen
Wong, Yi
Qiao, Xiao
Ho, Chin Pang
author_facet Bai, Wen
Wong, Yi
Qiao, Xiao
Ho, Chin Pang
contents Federated learning (FL) aims to train machine learning (ML) models collaboratively using decentralized data, bypassing the need for centralized data aggregation. Standard FL models often assume that all data come from the same unknown distribution. However, in practical situations, decentralized data frequently exhibit heterogeneity. We propose a novel FL model, Distributionally Robust Federated Learning (DRFL), that applies distributionally robust optimization to overcome the challenges posed by data heterogeneity and distributional ambiguity. We derive a tractable reformulation for DRFL and develop a novel solution method based on the alternating direction method of multipliers (ADMM) algorithm to solve this problem. Our experimental results demonstrate that DRFL outperforms standard FL models under data heterogeneity and ambiguity.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18436
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Distributionally Robust Federated Learning: An ADMM Algorithm
Bai, Wen
Wong, Yi
Qiao, Xiao
Ho, Chin Pang
Machine Learning
Federated learning (FL) aims to train machine learning (ML) models collaboratively using decentralized data, bypassing the need for centralized data aggregation. Standard FL models often assume that all data come from the same unknown distribution. However, in practical situations, decentralized data frequently exhibit heterogeneity. We propose a novel FL model, Distributionally Robust Federated Learning (DRFL), that applies distributionally robust optimization to overcome the challenges posed by data heterogeneity and distributional ambiguity. We derive a tractable reformulation for DRFL and develop a novel solution method based on the alternating direction method of multipliers (ADMM) algorithm to solve this problem. Our experimental results demonstrate that DRFL outperforms standard FL models under data heterogeneity and ambiguity.
title Distributionally Robust Federated Learning: An ADMM Algorithm
topic Machine Learning
url https://arxiv.org/abs/2503.18436