Near-optimal Differentially Private Client Selection in Federated Settings
This work addresses privacy and efficiency challenges in federated learning for applications like healthcare or finance, though it is incremental as it builds on existing client selection methods.
The paper tackles the problem of client selection in federated learning by developing an iterative differentially private algorithm that ensures near-optimal long-term average participation for clients, achieving a 95% efficiency rate compared to the optimal solution.
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.