Adaptive and Parallel Split Federated Learning in Vehicular Edge Computing

TL;DR

This paper introduces ASFV, an adaptive split federated learning framework for vehicular edge computing that reduces training latency by combining split learning and federated learning, considering vehicle heterogeneity and network dynamics.

Contribution

It proposes a novel adaptive split federated learning scheme that combines split learning and federated learning for vehicular edge computing, improving training efficiency and privacy.

Findings

Significantly reduces training latency compared to benchmarks.

Effectively adapts to network dynamics and vehicle mobility.

Maintains data privacy through split learning mechanisms.

Abstract

Vehicular edge intelligence (VEI) is a promising paradigm for enabling future intelligent transportation systems by accommodating artificial intelligence (AI) at the vehicular edge computing (VEC) system. Federated learning (FL) stands as one of the fundamental technologies facilitating collaborative model training locally and aggregation, while safeguarding the privacy of vehicle data in VEI. However, traditional FL faces challenges in adapting to vehicle heterogeneity, training large models on resource-constrained vehicles, and remaining susceptible to model weight privacy leakage. Meanwhile, split learning (SL) is proposed as a promising collaborative learning framework which can mitigate the risk of model wights leakage, and release the training workload on vehicles. SL sequentially trains a model between a vehicle and an edge cloud (EC) by dividing the entire model into a vehicle-side model and an EC-side model at a given cut layer. In this work, we combine the advantages of SL and FL to develop an Adaptive Split Federated Learning scheme for Vehicular Edge Computing (ASFV). The ASFV scheme adaptively splits the model and parallelizes the training process, taking into account mobile vehicle selection and resource allocation. Our extensive simulations, conducted on non-independent and identically distributed data, demonstrate that the proposed ASFV solution significantly reduces training latency compared to existing benchmarks, while adapting to network dynamics and vehicles' mobility.