Approximate Gradient Coding for Privacy-Flexible Federated Learning with Non-IID Data

arXiv:2404.03524v1 Announce Type: cross
Abstract: This work focuses on the challenges of non-IID data and stragglers/dropouts in federated learning. We introduce and explore a privacy-flexible paradigm that models parts of the clients' local data as non-private, offering a more versatile and business-oriented perspective on privacy. Within this framework, we propose a data-driven strategy for mitigating the effects of label heterogeneity and client straggling on federated learning. Our solution combines both offline data sharing and approximate gradient coding techniques. Through numerical …

arxiv business challenges clients coding cs.cr cs.dc cs.it cs.lg data federated federated learning framework local math.it non paradigm parts perspective privacy private stat.ml work