Clustered Vehicular Federated Learning: Process and Optimization

TL;DR

This paper introduces a clustered vehicular federated learning architecture that leverages V2V communication to improve scalability and learning accuracy in autonomous vehicle networks with limited resources and data heterogeneity.

Contribution

It proposes a novel vehicular FL architecture using clustering and V2V communication, optimizing for mobility, resource constraints, and data heterogeneity.

Findings

Improved learning accuracy on non-i.i.d datasets.

Effective clustering enhances communication efficiency.

Simulation results outperform standard FL methods.

Abstract

Federated Learning (FL) is expected to play a prominent role for privacy-preserving machine learning (ML) in autonomous vehicles. FL involves the collaborative training of a single ML model among edge devices on their distributed datasets while keeping data locally. While FL requires less communication compared to classical distributed learning, it remains hard to scale for large models. In vehicular networks, FL must be adapted to the limited communication resources, the mobility of the edge nodes, and the statistical heterogeneity of data distributions. Indeed, a judicious utilization of the communication resources alongside new perceptive learning-oriented methods are vital. To this end, we propose a new architecture for vehicular FL and corresponding learning and scheduling processes. The architecture utilizes vehicular-to-vehicular(V2V) resources to bypass the communication bottleneck where clusters of vehicles train models simultaneously and only the aggregate of each cluster is sent to the multi-access edge (MEC) server. The cluster formation is adapted for single and multi-task learning, and takes into account both communication and learning aspects. We show through simulations that the proposed process is capable of improving the learning accuracy in several non-independent and-identically-distributed (non-i.i.d) and unbalanced datasets distributions, under mobility constraints, in comparison to standard FL.