Differentially Private Online Federated Learning with Correlated Noise

arXiv:2403.16542v1 Announce Type: new
Abstract: We propose a novel differentially private algorithm for online federated learning that employs temporally correlated noise to improve the utility while ensuring the privacy of the continuously released models. To address challenges stemming from DP noise and local updates with streaming noniid data, we develop a perturbed iterate analysis to control the impact of the DP noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed under …

abstract algorithm arxiv challenges cs.cr cs.dc cs.lg data federated learning noise novel privacy stemming streaming type updates utility