《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (4): 1077-1085.DOI: 10.11772/j.issn.1001-9081.2024040428

• 人工智能 • 上一篇    下一篇

基于演化博弈的分层联邦学习边缘联合动态分析

项钰斐, 倪郑威()   

  1. 浙江工商大学 信息与电子工程学院,杭州 310018
  • 收稿日期:2024-04-10 修回日期:2024-06-27 接受日期:2024-07-04 发布日期:2025-04-08 出版日期:2025-04-10
  • 通讯作者: 倪郑威
  • 作者简介:项钰斐(1999—),男,浙江金华人,硕士研究生,主要研究方向:自然语言处理、机器学习
    倪郑威(1989—),男,湖北荆州人,副研究员,博士,CCF会员,主要研究方向:自然语言处理、机器学习。
  • 基金资助:
    浙江省自然科学基金资助项目(LQ22F010008)

Edge federation dynamic analysis for hierarchical federated learning based on evolutionary game

Yufei XIANG, Zhengwei NI()   

  1. School of Information and Electronic Engineering,Zhejiang Gongshang University,Hangzhou Zhejiang 310018,China
  • Received:2024-04-10 Revised:2024-06-27 Accepted:2024-07-04 Online:2025-04-08 Published:2025-04-10
  • Contact: Zhengwei NI
  • About author:XIANG Yufei, born in 1999, M. S. candidate. His research interests include natural language processing, machine learning.
    NI Zhengwei, born in 1989, Ph. D., associate research fellow. His research interests include natural language processing, machine learning.
  • Supported by:
    Zhejiang Provincial Natural Science Foundation(LQ22F010008)

摘要:

针对现有边缘服务器提供商(ESP)边缘资源有限导致的分层联邦学习的边缘节点服务质量(QoS)降低的问题,考虑边缘服务器潜在的边缘联合可能性,提出一种动态边缘联合框架(EFF)。所提框架内,不同的ESP相互协作,为分层联邦学习中由于客户端的异构性或数据的非独立同分布(Non-IID)等问题而降低的模型训练效率提供额外的边缘资源。首先,通过量化通信模型设定卸载决策,并将卸载任务发布给框架内其他ESP的边缘服务器,从而解决边缘资源的弹性化需求;其次,通过多轮迭代EFF参与策略(MIEPS)算法求解ESP之间的演化博弈均衡解,从而为ESP找到合适的资源分配策略;最后,通过理论和仿真实验验证均衡点的存在性、唯一性和稳定性。实验结果表明,相较于非联合策略和成对联合策略,通过MIEPS算法构建的三联EFF在基于独立同分布(IID)数据集训练得到的全局模型的预测准确率上分别提高了1.5和1.0个百分点,而在基于Non-IID数据集的准确率上分别提升了2.1和0.7个百分点。此外,通过改变ESP的资源配置方式,验证了EFF能够公平地分配ESP的报酬,激励更多的ESP参与其中,并形成良性的合作环境。

关键词: 分层联邦学习, 边缘联合, 任务卸载, 资源分配, 演化博弈

Abstract:

To address the issue that limited edge resources of the existing Edge Server Providers (ESPs) reduce the Quality of Service (QoS)of hierarchical federated learning edge nodes, a dynamic Edge Federated Framework (EFF)was proposed by considering the potential edge federation probability among edge servers. In the proposed framework, different ESPs cooperated to provide additional edge resources for hierarchical federated learning, which suffered from reduced model training efficiency due to client heterogeneity or Non-Independent and Identically Distributed (Non-IID)data. Firstly, decisions were offloaded by quantifying the communication model, and offloading tasks were assigned to the edge servers of other ESPs within the framework, so as to meet the elastic demand of edge resources. Secondly, the Multi-round Iterative EFF Participation Strategy (MIEPS)algorithm was used to solve the evolutionary game equilibrium solution among ESPs, thereby finding an appropriate resource allocation strategy. Finally, the existence, uniqueness, and stability of the equilibrium point were validated through theoretical and simulation experiments. Experimental results show that compared to non-federation and pairwise federation strategies, the tripartite EFF constructed using MIEPS algorithm improves the prediction accuracy of the global model trained on Independent and Identically Distributed (IID) datasets by 1.5 and 1.0 percentage points, respectively, and the prediction accuracy based on Non-IID datasets by 2.1 and 0.7 percentage points, respectively. Additionally, by changing the resource allocation method of ESP, it is validated that EFF can distribute the rewards of ESP fairly, encouraging more ESPs to participate and forming a positive cooperation environment.

Key words: hierarchical federated learning, edge federation, task offloading, resource allocation, evolutionary game

中图分类号: