面向非独立同分布数据的半监督联邦学习中自适应聚合的协作多智能体强化学习
Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data
- Institute of Communication Acoustics, Ruhr-Universität Bochum（鲁尔大学波鸿分校通信声学研究所）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
针对非独立同分布数据半监督联邦学习的挑战，提出pFedMARL方法，利用多智能体强化学习动态调整聚合策略，提升模型准确率、鲁棒性与公平性，性能优于FedAvg等方法。
中文摘要 AI 辅助
联邦学习（FL）可在保护数据隐私的同时实现机器学习模型的分布式训练，但FL难以应对异构、非独立同分布（non-IID）的客户端数据分布，导致全局模型次优且存在偏差。本文提出pFedMARL，这是一种利用带双延迟深度确定性策略梯度（TD3）的多智能体强化学习（MARL）的新方法，用于动态调整FL场景下的聚合策略。该方法采用服务端智能体调整客户端贡献以优化全局模型鲁棒性，客户端智能体平衡全局与本地更新以有效个性化模型，无需预训练。我们在半监督音频频谱图Transformer的训练中验证了pFedMARL的优越性能，在多种non-IID场景及存在对抗性客户端的情况下，其表现与FedAvg、Ditto和本地训练方法相当或更优。结果表明，pFedMARL可主动提升准确率、鲁棒性与公平性，适用于实际部署。
英文摘要
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.
