Entropy-based Client Selection Mechanism for Vehicular Federated Environments
John Lucas R. P. de Sousa, Wellington Lobato, Denis Lima do Rosário, Eduardo Cerqueira, Leandro Aparecido Villas · 2023
Autonomous driving requires machine learning models to be trained at the edge for improved efficiency and reduced communication latency. Federated learning (FL) allows knowledge sharing among all devices, but Not Independent and Identically Distributed (non-IID) scenarios with biased device data distributions can lead to statistical heterogeneity and lower classification accuracy. This paper proposes an entropy-based client selection approach for vehicular federated learning environments that aims to address the challenges posed by non-IID data in vehicular networks. The proposed method is compared to a random selection mechanism in both IID and non-IID scenarios, as well as in a scenario with random client drops. The results show that the entropy-based selection method outperforms the random selection method in all compared metrics, particularly in non-IID scenarios.