Architectural Blueprint For Heterogeneity-Resilient Federated Learning

arXiv:2403.04546v1 Announce Type: new
Abstract: This paper proposes a novel three tier architecture for federated learning to optimize edge computing environments. The proposed architecture addresses the challenges associated with client data heterogeneity and computational constraints. It introduces a scalable, privacy preserving framework that enhances the efficiency of distributed machine learning. Through experimentation, the paper demonstrates the architecture capability to manage non IID data sets more effectively than traditional federated learning models. Additionally, the paper highlights the potential of this innovative …

abstract architecture arxiv challenges client computational computing constraints cs.dc cs.lg cs.ni data distributed edge edge computing efficiency environments experimentation federated learning framework machine machine learning novel paper privacy privacy preserving resilient scalable through type