Locally Differentially Private Online Federated Learning With Correlated Noise
This work addresses privacy-preserving machine learning for distributed systems with streaming data, though it appears incremental as it builds on existing LDP and federated learning methods.
The paper tackles the problem of maintaining privacy in online federated learning with streaming non-IID data by introducing a locally differentially private algorithm that uses temporally correlated noise to improve utility. It establishes a dynamic regret bound under an (ε,δ)-LDP budget and demonstrates effectiveness through numerical experiments.
We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To address challenges posed by the correlated noise and local updates with streaming non-IID data, we develop a perturbed iterate analysis that controls the impact of the noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed for several classes of nonconvex loss functions. Subject to an $(ε,δ)$-LDP budget, we establish a dynamic regret bound that quantifies the impact of key parameters and the intensity of changes in the dynamic environment on the learning performance. Numerical experiments confirm the efficacy of the proposed algorithm.