移动通信2024，Vol.48Issue(6)：91-96,6.DOI:10.3969/j.issn.1006-1010.20231227-0001
基于端边云协同体系的联邦学习模型训练与优化
Training and Optimization of Federated Learning Models Based on End Edge Cloud Collaborative System
摘要
Abstract
In response to the problem that federated learning training models are easily affected by data attributes,a federated learning model training and optimization method based on end-edge-cloud collaborative system is proposed.This method introduces credibility and dynamic learning rate to achieve self-learning and self-optimization of global model parameters.Experiments have shown that compared with other algorithms,the proposed algorithm fully considers the credibility of the edge,which can prevent the rapid decrease in accuracy caused by rapid changes in global model parameters due to data distribution or quality issues.In addition,due to the introduction of dynamic learning rate,the global model can adaptively adjust the learning rate based on the error of the local model during aggregation,which to a certain extent balances the global parameter update speed and algorithm stability.关键词
端边云协同/模型聚合/联邦学习/可信度/动态学习率Key words
end-edge-cloud collaboration/model aggregation/federated learning/credibility/dynamic learning rate分类
电子信息工程引用本文复制引用
陈少权,杜翠凤,张振..基于端边云协同体系的联邦学习模型训练与优化[J].移动通信,2024,48(6):91-96,6.基金项目
广东省海洋经济发展(海洋六大产业)专项资金项目"面向海洋产业的探测通信一体化立体海洋无线网络系统研究"(粤自然资合[2023]24号) （海洋六大产业）
