Near-optimal Differentially Private Client Selection in Federated Settings

TL;DR

This paper introduces a differentially private iterative client selection algorithm for federated learning that optimizes long-term participation while preserving privacy, without requiring client-to-client communication.

Contribution

It presents a novel privacy-preserving client selection algorithm that achieves near-optimal participation in federated settings without client-to-client info exchange.

Findings

Algorithm achieves near-optimal long-term participation.

Provides differential privacy guarantees.

Experimental results confirm efficacy.

Abstract

We develop an iterative differentially private algorithm for client selection in federated settings. We consider a federated network wherein clients coordinate with a central server to complete a task; however, the clients decide whether to participate or not at a time step based on their preferences -- local computation and probabilistic intent. The algorithm does not require client-to-client information exchange. The developed algorithm provides near-optimal values to the clients over long-term average participation with a certain differential privacy guarantee. Finally, we present the experimental results to check the algorithm's efficacy.