Near-optimal Differentially Private Client Selection in Federated Settings
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.
Cite
@article{arxiv.2310.09370,
title = {Near-optimal Differentially Private Client Selection in Federated Settings},
author = {Syed Eqbal Alam and Dhirendra Shukla and Shrisha Rao},
journal= {arXiv preprint arXiv:2310.09370},
year = {2023}
}
Comments
To appear in the proceedings of the 59th Annual Allerton Conference on Communication, Control, and Computing, September 2023, Monticello, Illinois, USA