Learning-Based Client Selection for Federated Learning Services Over Wireless Networks with Constrained Monetary Budgets

TL;DR

This paper proposes a deep reinforcement learning approach for dynamic client selection in federated learning over wireless networks, optimizing training performance under monetary constraints.

Contribution

It introduces a multi-agent hybrid deep reinforcement learning algorithm to jointly optimize client selection and payments in federated learning with multiple services.

Findings

Significant improvement in training performance with the proposed algorithm

Effective handling of dynamic datasets and monetary budgets

Avoidance of action conflicts in client selection

Abstract

We investigate a data quality-aware dynamic client selection problem for multiple federated learning (FL) services in a wireless network, where each client offers dynamic datasets for the simultaneous training of multiple FL services, and each FL service demander has to pay for the clients under constrained monetary budgets. The problem is formalized as a non-cooperative Markov game over the training rounds. A multi-agent hybrid deep reinforcement learning-based algorithm is proposed to optimize the joint client selection and payment actions, while avoiding action conflicts. Simulation results indicate that our proposed algorithm can significantly improve training performance.