VREM-FL: Mobility-Aware Computation-Scheduling Co-Design for Vehicular Federated Learning

• Published in: IEEE transactions on vehicular technology Vol. 74; no. 2; pp. 3311 - 3326
• Main Authors: Ballotta, Luca, Fabbro, Nicolo Dal, Perin, Giovanni, Schenato, Luca, Rossi, Michele, Piro, Giuseppe
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 5G mobile communication; Adaptive algorithms; Artificial intelligence; Artificial neural networks; Co-design; Computation; Computational modeling; Costs; Design optimization; Federated learning; Image segmentation; Intelligent vehicles; Machine learning; Optimization; Processor scheduling; Regression models; REM; Resource management; Resource scheduling; Scheduling; Smart sensors; Training; vehicular networks; Windows (intervals); Wireless networks
• ISSN: 0018-9545; 1939-9359
• DOI: 10.1109/TVT.2024.3479780

Assisted and autonomous driving are rapidly gaining momentum and will soon become a reality. Artificial intelligence and machine learning are regarded as key enablers thanks to the massive amount of data that smart vehicles will collect from onboard sensors. Federated learning is one of the most promising techniques for training global machine learning models while preserving data privacy of vehicles and optimizing communications resource usage. In this article, we propose vehicular radio environment map federated learning (VREM-FL), a computation-scheduling co-design for vehicular federated learning that combines mobility of vehicles with 5G radio environment maps. VREM-FL jointly optimizes learning performance of the global model and wisely allocates communication and computation resources. This is achieved by orchestrating local computations at the vehicles in conjunction with transmission of their local models in an adaptive and predictive fashion, by exploiting radio channel maps. The proposed algorithm can be tuned to trade training time for radio resource usage. Experimental results demonstrate that VREM-FL outperforms literature benchmarks for both a linear regression model (learning time reduced by 28%) and a deep neural network for semantic image segmentation (doubling the number of model updates within the same time window).