Mobility-Aware Federated Learning: Multi-Armed Bandit Based Selection in Vehicular Network

TL;DR

This paper introduces a mobility-aware federated learning scheme for vehicular networks, using a multi-armed bandit algorithm to select vehicles, which improves training efficiency and convergence speed.

Contribution

It proposes a novel vehicle selection method based on real-time participation ratios and multi-armed bandits, addressing mobility challenges in vehicular federated learning.

Findings

Achieves approximately 28% faster convergence than baselines.

Demonstrates the effectiveness of mobility-aware vehicle selection.

Analyzes the impact of vehicle mobility on training loss.

Abstract

In this paper, we study a vehicle selection problem for federated learning (FL) over vehicular networks. Specifically, we design a mobility-aware vehicular federated learning (MAVFL) scheme in which vehicles drive through a road segment to perform FL. Some vehicles may drive out of the segment which leads to unsuccessful training. In the proposed scheme, the real-time successful training participation ratio is utilized to implement vehicle selection. We conduct the convergence analysis to indicate the influence of vehicle mobility on training loss. Furthermore, we propose a multi-armed bandit-based vehicle selection algorithm to minimize the utility function considering training loss and delay. The simulation results show that compared with baselines, the proposed algorithm can achieve better training performance with approximately 28\% faster convergence.