用多智能体强化学习动态调整联邦学习聚合策略，提升非独立同分布数据下的模型性能。
Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data
- 服务器与客户端各设智能体，通过TD3算法自适应调节参与权重
- 在多种非独立同分布场景下，准确率超越FedAvg、Ditto等主流方法
- 适用于有对抗性客户端的真实场景，兼顾模型精度与公平性
联邦学习（FL）可在保护数据隐私的前提下实现分布式模型训练，但面临客户端数据异构、非独立同分布（non-IID）的问题，导致全局模型次优且存在偏差。本文提出pFedMARL，一种基于多智能体强化学习（MARL）与双延迟深度确定性策略梯度（TD3）的新型方法，用于动态调整联邦学习中的聚合策略。服务器端智能体根据贡献度调整客户端权重，以优化全局模型鲁棒性；客户端智能体则平衡全局与本地更新，实现个性化建模而无需预训练。实验表明，pFedMARL在半监督音频光谱变换器训练中表现优异，在多个non-IID场景及存在恶意客户端的情况下，性能匹配或优于FedAvg、Ditto和本地训练。结果表明，该方法显著提升了准确性、鲁棒性与公平性，具备实际部署潜力。
原文摘要 · Abstract (English)
Federated Learning (FL) enables distributed training of machine learning models while preserving data privacy. However, FL struggles with heterogeneous, non-IID client data distributions, resulting in sub-optimal and biased global models. In this paper, we propose pFedMARL, a novel approach leveraging Multi-Agent Reinforcement Learning (MARL) with Twin Delayed Deep Deterministic Policy Gradient (TD3) to dynamically adapt aggregation strategies in FL settings. Our method employs a server-side agent adjusting client contributions to optimize global model robustness and client-side agents balancing global and local updates to personalize models effectively without pre-training. We demonstrate superior performance of pFedMARL for training a semi-supervised audio spectrogram transformer, matching or outperforming FedAvg, Ditto, and local training approaches across multiple non-IID scenarios and in the presence of adversarial clients. Our results indicate that pFedMARL actively improves accuracy, robustness, and fairness, making it suitable for real-world deployments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。