A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning

TL;DR

This paper introduces FedMarl, a multi-agent reinforcement learning framework for federated learning that optimizes client selection to enhance training efficiency, reducing latency and communication costs while maintaining high model accuracy.

Contribution

It presents FedMarl, a novel MARL-based client selection method that jointly optimizes accuracy, latency, and communication efficiency in federated learning.

Findings

FedMarl significantly improves model accuracy.

It reduces processing latency.

It lowers communication costs.

Abstract

Federated learning (FL) is a training technique that enables client devices to jointly learn a shared model by aggregating locally-computed models without exposing their raw data. While most of the existing work focuses on improving the FL model accuracy, in this paper, we focus on the improving the training efficiency, which is often a hurdle for adopting FL in real-world applications. Specifically, we design an efficient FL framework which jointly optimizes model accuracy, processing latency and communication efficiency, all of which are primary design considerations for real implementation of FL. Inspired by the recent success of Multi-Agent Reinforcement Learning (MARL) in solving complex control problems, we present \textit{FedMarl}, an MARL-based FL framework which performs efficient run-time client selection. Experiments show that FedMarl can significantly improve model accuracy with much lower processing latency and communication cost.