On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness

TL;DR

This paper introduces FLAME, an ADMM-based framework for personalized and global federated learning that improves convergence, robustness, fairness, and accuracy in heterogeneous data environments.

Contribution

The paper proposes FLAME, a novel ADMM-based optimization framework for federated learning that jointly trains personalized and global models with theoretical convergence guarantees.

Findings

FLAME outperforms state-of-the-art methods in convergence and accuracy.

FLAME achieves higher test accuracy under various attacks.

FLAME provides more uniform performance across clients.

Abstract

Statistical heterogeneity is a root cause of tension among accuracy, fairness, and robustness of federated learning (FL), and is key in paving a path forward. Personalized FL (PFL) is an approach that aims to reduce the impact of statistical heterogeneity by developing personalized models for individual users, while also inherently providing benefits in terms of fairness and robustness. However, existing PFL frameworks focus on improving the performance of personalized models while neglecting the global model. Moreover, these frameworks achieve sublinear convergence rates and rely on strong assumptions. In this paper, we propose FLAME, an optimization framework by utilizing the alternating direction method of multipliers (ADMM) to train personalized and global models. We propose a model selection strategy to improve performance in situations where clients have different types of heterogeneous data. Our theoretical analysis establishes the global convergence and two kinds of convergence rates for FLAME under mild assumptions. We theoretically demonstrate that FLAME is more robust and fair than the state-of-the-art methods on a class of linear problems. Our experimental findings show that FLAME outperforms state-of-the-art methods in convergence and accuracy, and it achieves higher test accuracy under various attacks and performs more uniformly across clients.