Age Aware Scheduling for Differentially-Private Federated Learning

arXiv:2405.05962v1 Announce Type: new
Abstract: This paper explores differentially-private federated learning (FL) across time-varying databases, delving into a nuanced three-way tradeoff involving age, accuracy, and differential privacy (DP). Emphasizing the potential advantages of scheduling, we propose an optimization problem aimed at meeting DP requirements while minimizing the loss difference between the aggregated model and the model obtained without DP constraints. To harness the benefits of scheduling, we introduce an age-dependent upper bound on the loss, leading to the development of …

abstract accuracy advantages age arxiv cs.it cs.lg cs.lo databases difference differential differential privacy federated learning loss math.it optimization paper privacy requirements scheduling type while