Robust Federated Learning against Model Perturbation in Edge Networks

TL;DR

This paper introduces SMRFL, a federated learning method that enhances model robustness against perturbations by promoting flat minima, ensuring reliable performance in edge networks with model disturbances.

Contribution

The paper proposes a novel Sharpness-Aware Minimization-based approach for robust federated learning, addressing perturbations with theoretical convergence guarantees and empirical robustness improvements.

Findings

SMRFL significantly outperforms baseline methods under various perturbations.

Theoretical analysis confirms convergence rate similar to standard FL.

Experimental results on real datasets demonstrate enhanced robustness.

Abstract

Federated Learning (FL) is a promising paradigm for realizing edge intelligence, allowing collaborative learning among distributed edge devices by sharing models instead of raw data. However, the shared models are often assumed to be ideal, which would be inevitably violated in practice due to various perturbations, leading to significant performance degradation. To overcome this challenge, we propose a novel method, termed Sharpness-Aware Minimization-based Robust Federated Learning (SMRFL), which aims to improve model robustness against perturbations by exploring the geometrical property of the model landscape. Specifically, SMRFL solves a min-max optimization problem that promotes model convergence towards a flat minimum by minimizing the maximum loss within a neighborhood of the model parameters. In this way, model sensitivity to perturbations is reduced, and robustness is enhanced since models in the neighborhood of the flat minimum also enjoy low loss values. The theoretical result proves that SMRFL can converge at the same rate as FL without perturbations. Extensive experimental results show that SMRFL significantly enhances robustness against perturbations compared to three baseline methods on two real-world datasets under three perturbation scenarios.