arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.02458cs.LGcs.NI
收藏

多服务器联邦学习中的冲突感知客户端选择

Conflict-Aware Client Selection for Multi-Server Federated Learning

1 School of Computer;Information Engineering, Xiamen University of Technology, Xiamen, China;2 Department of Electrical;Electronic Engineering, The University of Hong Kong, Hong Kong, China;3 Department of Computer Science, City University of Hong Kong, Hong Kong, China;4 School of Software \& Microelectronics, Peking University, Beijing, China;5 Institute for Imaging, Data;Communications, University of Edinburgh, UK

Mingwei Hong, Zheng Lin, Zehang Lin, Lin Li, Miao Yang, Xia Du, Zihan Fang, Zhaolu Kang, Dianxin Luan, Shunzhi Zhu

AI总结:

本文提出RL CRP方法,通过预测冲突风险优化多服务器联邦学习中的客户端选择,减少资源竞争并提升训练效率。

摘要:

联邦学习(FL)作为一种有前途的分布式机器学习(ML)方法,能够使客户端在不暴露原始数据的情况下协同训练模型,从而保护用户隐私并减少通信成本。尽管有这些优势,传统的单服务器FL由于需要聚合大量客户端的模型而面临较高的通信延迟。虽然多服务器FL将工作负载分布到边缘服务器上,但重叠的客户端覆盖和缺乏协调的选择往往导致资源竞争,引起带宽冲突和训练失败。为了解决这些限制,我们提出了一种去中心化的强化学习与冲突风险预测相结合的方法,称为RL CRP,以优化多服务器FL系统中的客户端选择。具体而言,每个服务器利用其稀疏的历史客户端选择序列,通过分类隐马尔可夫模型估计客户端选择冲突的可能性。然后,引入一个公平性意识的奖励机制,以促进长期客户端参与,从而最小化训练延迟和资源竞争。广泛的实验表明,所提出的RL-CRP框架有效减少了服务器间的冲突,并在收敛速度和通信成本方面显著提高了训练效率。

英文摘要:

Federated learning (FL) has emerged as a promising distributed machine learning (ML) that enables collaborative model training across clients without exposing raw data, thereby preserving user privacy and reducing communication costs. Despite these benefits, traditional single-server FL suffers from high communication latency due to the aggregation of models from a large number of clients. While multi-server FL distributes workloads across edge servers, overlapping client coverage and uncoordinated selection often lead to resource contention, causing bandwidth conflicts and training failures. To address these limitations, we propose a decentralized reinforcement learning with conflict risk prediction, named RL CRP, to optimize client selection in multi-server FL systems. Specifically, each server estimates the likelihood of client selection conflicts using a categorical hidden Markov model based on its sparse historical client selection sequence. Then, a fairness-aware reward mechanism is incorporated to promote long-term client participation for minimizing training latency and resource contention. Extensive experiments demonstrate that the proposed RL-CRP framework effectively reduces inter-server conflicts and significantly improves training efficiency in terms of convergence speed and communication cost.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑