Distribution-Aware Mobility-Assisted Decentralized Federated Learning

TL;DR

This paper explores how strategic mobility of clients in decentralized federated learning can improve model accuracy and convergence by enhancing information flow and mitigating data heterogeneity.

Contribution

It introduces distribution-aware mobility strategies that leverage data distribution knowledge to improve decentralized federated learning performance.

Findings

Mobile clients with random movement improve accuracy.

Distribution-aware mobility patterns outperform random movement.

Enhanced mobility strategies mitigate data heterogeneity effects.

Abstract

Decentralized federated learning (DFL) has attracted significant attention due to its scalability and independence from a central server. In practice, some participating clients can be mobile, yet the impact of user mobility on DFL performance remains largely unexplored, despite its potential to facilitate communication and model convergence. In this work, we demonstrate that introducing a small fraction of mobile clients, even with random movement, can significantly improve the accuracy of DFL by facilitating information flow. To further enhance performance, we propose novel distribution-aware mobility patterns, where mobile clients strategically navigate the network, leveraging knowledge of data distributions and static client locations. The proposed moving strategies mitigate the impact of data heterogeneity and boost learning convergence. Extensive experiments validate the effectiveness of induced mobility in DFL and demonstrate the superiority of our proposed mobility patterns over random movement.