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.
View on arXiv@article{bai2025_2503.18436,
title={ Distributionally Robust Federated Learning: An ADMM Algorithm },
author={ Wen Bai and Yi Wong and Xiao Qiao and Chin Pang Ho },
journal={arXiv preprint arXiv:2503.18436},
year={ 2025 }
}