SFETEC: Split-FEderated Learning Scheme Optimized for Thing-Edge-Cloud Environment

Abstract

This paper introduces SFETEC, an innovative federated learning framework addressing the limitations of traditional methods like FedAvg. SFETEC splits training into base models and core models, reducing communication overhead, mitigating non-IID data issues, and enhancing training speed. Base models are trained at client devices, while core models are trained at edge servers and aggregated at the cloud. Preliminary results show that SFETEC significantly reduces communication overhead and training duration compared to the state-of-the-art baselines while enhancing privacy.