Age Aware Scheduling for Differentially-Private Federated Learning

TL;DR

This paper introduces an age-aware scheduling approach for differentially-private federated learning, optimizing the tradeoff between privacy, model accuracy, and data freshness to improve performance.

Contribution

It proposes an age-dependent scheduling framework that balances privacy and accuracy in federated learning, a novel approach not previously explored.

Findings

Proposed an age-aware scheduling scheme outperforming classic DP FL.

Demonstrated improved accuracy and privacy tradeoff through simulations.

Provided insights into the interplay of age, accuracy, and privacy in FL.

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 an age-aware scheduling design. Simulation results underscore the superior performance of our proposed scheme compared to FL with classic DP, which does not consider scheduling as a design factor. This research contributes insights into the interplay of age, accuracy, and DP in federated learning, with practical implications for scheduling strategies.