摘要
针对算力网络中终端的异构性而导致的设备资源不均衡以及各终端动态加入或离开联邦学习任务导致协同体系不稳定、内生全局模型收敛性差等问题,文中提出了一种面向算力网络的软掩码策略梯度(Soft-Masked Policy Gra⁃dient,SMPG)联邦学习算法。该算法能通过联合计算优化机理,自适应地调整异构终端局部模型来更新频率与聚合时间,以合理分配终端计算及通信资源,提升联邦学习内生模型的收敛速度及终端的资源利用率。
Aiming at the imbalance of equipment resources caused by the heterogeneity of end points in computing power networks,the instability of the cooperative system caused by the dynamic addition or departure of each end point from federated learning tasks,and the poor convergence of the endogenous global model.This paper proposes a soft-mask policy layer(SMPG)federated learning algorithm for computing power networks.The algorithm can adaptively adjust the heterogeneous end point local model to update the frequency and aggregation time through the joint computing optimization mechanism,so as to rationally allocate end point computing and communication resources,improve the convergence speed of the federated learning endogenous model and the resource utilization rate of the end point.
作者
杨慧娉
赖小龙
高勇
YANG Huiping;LAI Xiaolong;GAO Yong(Chongqing College of Mobile Communication,College of Communication and Information Engineering,Chongqing 401520,China;Chongqing College of Mobile Communication,Chongqing Key Laboratory of Public Big Data Security Technology,Chongqing 401420,China)
出处
《移动信息》
2024年第8期254-256,共3页
MOBILE INFORMATION
基金
重庆移通学院首批课堂教学改革项目:人工智能原理(23JG2079)
重庆移通学院高等教育教学改革研究项目一般项目:新工科视角下网络安全虚拟化攻防演练平台建设与应用(YTJG202128)。
关键词
算力网络
异构终端
软掩码
Computing power network
Heterogeneous terminal
Soft mask