Optimized Local Updates In Federated Learning Via Reinforcement Learning

Abstract

Federated Learning (FL) is a distributed framework for collaborative model training over large-scale distributed data, enabling higher performance while maintaining client data privacy. However, the nature of model aggregation at the centralized server can result in a performance drop in the presence of non-IID data across different clients. We remark that training a client locally on more data than necessary does not benefit the overall performance of all clients. In this paper, we devise a novel framework that leverages a Deep Reinforcement Learning (DRL) agent to select an optimized amount of data necessary to train a client model without oversharing information with the server. Starting without awareness of the client's performance, the DRL agent utilizes the change in training loss as a reward signal and learns to optimize the amount of training data necessary for improving the client's performance. Specifically, after each aggregation round, the DRL algorithm considers the local

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymurad2025optimized

Related papers

• A Fair Federated Learning Framework With Reinforcement Learning (2022)0.00
• A Multi-agent Reinforcement Learning Approach For Efficient Client Selection In Federated Learning (2022)15.00
• Dearfsac: An Approach To Optimizing Unreliable Federated Learning Via Deep Reinforcement Learning (2022)0.00
• Federated Ensemble Model-based Reinforcement Learning In Edge Computing (2021)11.58
• Heterogeneity-aware Personalized Federated Learning Via Adaptive Dual-agent Reinforcement Learning (2025)0.00
• Communication-efficient Consensus Mechanism For Federated Reinforcement Learning (2022)6.77
• Adaptive Incentive For Cross-silo Federated Learning: A Multi-agent Reinforcement Learning Approach (2023)10.74
• Fedmrl: Data Heterogeneity Aware Federated Multi-agent Deep Reinforcement Learning For Medical Imaging (2024)0.00