Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networks
This addresses the challenge of training models in mobile vehicular networks with edge-level data heterogeneity, offering a novel perspective on mobility as a benefit rather than a drawback, though it is incremental in applying existing HFL to a specific domain.
The paper tackles the problem of hierarchical federated learning (HFL) in vehicular networks with mobile devices, showing through convergence analysis that mobility accelerates convergence by fusing data and shuffling models, and simulation results demonstrate up to 15.1% higher model accuracy on CIFAR-10.
Hierarchical federated learning (HFL) enables distributed training of models across multiple devices with the help of several edge servers and a cloud edge server in a privacy-preserving manner. In this paper, we consider HFL with highly mobile devices, mainly targeting at vehicular networks. Through convergence analysis, we show that mobility influences the convergence speed by both fusing the edge data and shuffling the edge models. While mobility is usually considered as a challenge from the perspective of communication, we prove that it increases the convergence speed of HFL with edge-level heterogeneous data, since more diverse data can be incorporated. Furthermore, we demonstrate that a higher speed leads to faster convergence, since it accelerates the fusion of data. Simulation results show that mobility increases the model accuracy of HFL by up to 15.1% when training a convolutional neural network on the CIFAR-10 dataset.