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

2022/01/09 by Sai Qian Zhang, Zhang, Sai Qian, Jieyu Lin +3 · 5 citations
Computer Science · Psychology · #Artificial Intelligence (cs.AI) #Data Stream Mining Techniques #Digital Mental Health Interventions #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2201.02932

openalex publication_date 2022/01/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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 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.

Cited by

• DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving
• BIPPO: Budget-Aware Independent PPO for Energy-Efficient Federated Learning Services
• Pareto Actor-Critic for Communication and Computation Co-Optimization in Non-Cooperative Federated Learning Services
• Fairness in Federated Learning: Trends, Challenges, and Opportunities
• Proxy Model-Guided Reinforcement Learning for Client Selection in Federated Recommendation

Related

• A Fair Federated Learning Framework With Reinforcement Learning
• Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach
• Towards Optimal Heterogeneous Client Sampling in Multi-Model Federated Learning
• Optimized Local Updates in Federated Learning via Reinforcement Learning
• FilFL: Client Filtering for Optimized Client Participation in Federated Learning