Data-Heterogeneous Hierarchical Federated Learning with Mobility
This work addresses data heterogeneity and mobility challenges in federated learning for vehicular networks, representing an incremental improvement by leveraging mobility to mitigate data skew.
The paper tackles the problem of data heterogeneity in hierarchical federated learning (HFL) within vehicular networks by analyzing how mobility impacts convergence and exploiting it to improve learning performance, showing that mobility can increase model accuracy by up to 15.1% on CIFAR-10.
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.