用强化学习动态选最优客户端，加速无线联邦学习。
Adaptive Client Selection via Q-Learning-based Whittle Index in Wireless Federated Learning
- 基于Q-learning自适应更新客户端优先级指数
- 比现有方法快20%以上达成目标准确率
- 无需知道客户端状态变化规律，适合真实场景
我们研究无线联邦学习中的客户端选择问题，目标是减少达到特定学习精度所需的总时间。由于服务器无法观测客户端动态状态（影响计算与通信效率），我们将客户端选择建模为一个非平稳多臂老虎机问题。提出一种名为联邦Q-learning中威特指数学习（WILF-Q）的可扩展高效方法，利用Q-learning自适应学习并更新每个客户端的近似威特指数，进而选择指数最高的客户端。相比现有方法，WILF-Q无需预先知晓客户端状态转移或数据分布，更适用于实际联邦学习部署。实验表明，WILF-Q在学习效率上显著优于现有基线策略，提供了一种鲁棒高效的无线联邦学习客户端选择方案。
原文摘要 · Abstract (English)
We consider the client selection problem in wireless Federated Learning (FL), with the objective of reducing the total required time to achieve a certain level of learning accuracy. Since the server cannot observe the clients' dynamic states that can change their computation and communication efficiency, we formulate client selection as a restless multi-armed bandit problem. We propose a scalable and efficient approach called the Whittle Index Learning in Federated Q-learning (WILF-Q), which uses Q-learning to adaptively learn and update an approximated Whittle index associated with each client, and then selects the clients with the highest indices. Compared to existing approaches, WILF-Q does not require explicit knowledge of client state transitions or data distributions, making it well-suited for deployment in practical FL settings. Experiment results demonstrate that WILF-Q significantly outperforms existing baseline policies in terms of learning efficiency, providing a robust and efficient approach to client selection in wireless FL.
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。