Distributionally Robust Federated Learning: An ADMM Algorithm
This addresses data heterogeneity issues in federated learning for decentralized applications, but it is incremental as it builds on existing optimization methods.
The paper tackles the problem of data heterogeneity in federated learning by proposing a distributionally robust optimization model, and experimental results show it outperforms standard federated learning models under such conditions.
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.