Robust Decentralized Learning with Local Updates and Gradient Tracking

TL;DR

This paper introduces Dec-FedTrack, a decentralized learning algorithm combining local updates and gradient tracking to enhance robustness and efficiency in heterogeneous data environments, with proven convergence and empirical validation.

Contribution

It proposes a novel decentralized minimax optimization method that addresses data heterogeneity and adversarial robustness through local updates and gradient tracking.

Findings

Converges to a stationary point in nonconvex-strongly concave settings.

Theoretical analysis confirms convergence properties.

Numerical experiments support the theoretical results.

Abstract

As distributed learning applications such as Federated Learning, the Internet of Things (IoT), and Edge Computing grow, it is critical to address the shortcomings of such technologies from a theoretical perspective. As an abstraction, we consider decentralized learning over a network of communicating clients or nodes and tackle two major challenges: data heterogeneity and adversarial robustness. We propose a decentralized minimax optimization method that employs two important modules: local updates and gradient tracking. Minimax optimization is the key tool to enable adversarial training for ensuring robustness. Having local updates is essential in Federated Learning (FL) applications to mitigate the communication bottleneck, and utilizing gradient tracking is essential to proving convergence in the case of data heterogeneity. We analyze the performance of the proposed algorithm, Dec-FedTrack, in the case of nonconvex-strongly concave minimax optimization, and prove that it converges a stationary point. We also conduct numerical experiments to support our theoretical findings.