Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning

arXiv:2311.09441v3 Announce Type: replace-cross
Abstract: Split Federated Learning (SFL) has recently emerged as a promising distributed learning technology, leveraging the strengths of both federated and split learning. It emphasizes the advantages of rapid convergence while addressing privacy concerns. As a result, this innovation has received significant attention from both industry and academia. However, since the model is split at a specific layer, known as a cut layer, into both client-side and server-side models for the SFL, the choice of the …

arxiv attention convergence cs.ai cs.cr cs.lg distributed energy federated federated learning industry innovation privacy privacy concerns rapid result split learning technology