Data-Heterogeneous Hierarchical Federated Learning with Mobility

TL;DR

This paper investigates how mobility in vehicular networks affects hierarchical federated learning, showing that mobility can be exploited to enhance model accuracy despite data heterogeneity.

Contribution

It derives the convergence bounds of HFL considering mobility and demonstrates how mobility can be used to mitigate data heterogeneity for better performance.

Findings

Mobility can improve model accuracy by up to 15.1%.

Mobility impacts HFL performance and convergence.

Simulation results verify the theoretical analysis.

Abstract

Federated learning enables distributed training of machine learning (ML) models across multiple devices in a privacy-preserving manner. Hierarchical federated learning (HFL) is further proposed to meet the requirements of both latency and coverage. In this paper, we consider a data-heterogeneous HFL scenario with mobility, mainly targeting vehicular networks. We derive the convergence upper bound of HFL with respect to mobility and data heterogeneity, and analyze how mobility impacts the performance of HFL. While mobility is considered as a challenge from a communication point of view, our goal here is to exploit mobility to improve the learning performance by mitigating data heterogeneity. Simulation results verify the analysis and show that mobility can indeed improve the model accuracy by up to 15.1\% when training a convolutional neural network on the CIFAR-10 dataset using HFL.