Enabling Intelligent Vehicular Networks Through Distributed Learning in the Non-Terrestrial Networks 6G Vision
David Naseh, Swapnil Sadashiv Shinde, Daniele Tarchi
TL;DR
The paper tackles the challenge of delivering privacy-preserving, low-latency learning for 6G ITS in non-terrestrial networks. It introduces Federated Split Transfer Learning (FSTL), a framework that combines Transfer Learning, Split Learning, and Federated Learning, executed on High Altitude Platforms to enable efficient, parallel training with intermediate representations. Key contributions include a detailed FSTL architecture, a latency analysis contrasting FL, SL, FSL, and FSTL, and simulation results using AlexNet on MNIST demonstrating faster convergence and robustness to participant heterogeneity. The work shows that FSTL can reduce training time and communication overhead while maintaining accuracy, signaling a practical path toward intelligent, NTN-based vehicular networks, albeit with domain shift and drift challenges that warrant further study.
Abstract
The forthcoming 6G-enabled Intelligent Transportation System (ITS) is set to redefine conventional transportation networks with advanced intelligent services and applications. These technologies, including edge computing, Machine Learning (ML), and network softwarization, pose stringent requirements for latency, energy efficiency, and user data security. Distributed Learning (DL), such as Federated Learning (FL), is essential to meet these demands by distributing the learning process at the network edge. However, traditional FL approaches often require substantial resources for satisfactory learning performance. In contrast, Transfer Learning (TL) and Split Learning (SL) have shown effectiveness in enhancing learning efficiency in resource-constrained wireless scenarios like ITS. Non-terrestrial Networks (NTNs) have recently acquired a central place in the 6G vision, especially for boosting the coverage, capacity, and resilience of traditional terrestrial facilities. Air-based NTN layers, such as High Altitude Platforms (HAPs), can have added advantages in terms of reduced transmission distances and flexible deployments and thus can be exploited to enable intelligent solutions for latency-critical vehicular scenarios. With this motivation, in this work, we introduce the concept of Federated Split Transfer Learning (FSTL) in joint air-ground networks for resource-constrained vehicular scenarios. Simulations carried out in vehicular scenarios validate the efficacy of FSTL on HAPs in NTN, demonstrating significant improvements in addressing the demands of ITS applications.