Split Federated Learning Empowered Vehicular Edge Intelligence: Concept, Adaptive Design and Future Directions

TL;DR

This paper introduces Adaptive Split Federated Learning (ASFL) for vehicular edge intelligence, enhancing communication efficiency and model performance in dynamic vehicular networks with non-IID data.

Contribution

The paper proposes ASFL, a novel adaptive SFL scheme that dynamically optimizes cut layer selection for improved efficiency and performance in vehicular edge intelligence.

Findings

ASFL adapts cut layer selection based on network conditions.

ASFL improves communication and computation efficiency.

ASFL enhances model accuracy in non-IID data scenarios.

Abstract

To achieve ubiquitous intelligence in future vehicular networks, artificial intelligence (AI) is essential for extracting valuable insights from vehicular data to enhance AI-driven services. By integrating AI technologies into Vehicular Edge Computing (VEC) platforms, which provides essential storage, computing, and network resources, Vehicular Edge Intelligence (VEI) can be fully realized. Traditional centralized learning, as one of the enabling technologies for VEI, places significant strain on network bandwidth while also increasing latency and privacy concerns. Nowadays, distributed machine learning methods, such as Federated Learning (FL), Split Learning (SL), and Split Federated Learning (SFL), are widely applied in vehicular networks to support VEI. However, these methods still face significant challenges due to the mobility and constrained resources inherent in vehicular networks. In this article, we first provide an overview of the system architecture, performance metrics, and challenges associated with VEI design. Then, the adaptive design of SFL, namely Adaptive Split Federated Learning (ASFL) is introduced. The proposed ASFL scheme dynamically adapts the cut layer selection process and operates in parallel, optimizing both communication and computation efficiency while improving model performance under non-IID data distribution. Finally, we highlight future research directions to shed the light on the efficient design of SFL.