ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Optimizing Aggregation Frequency for Hierarchical Model Training in Heterogeneous Edge Computing

Yang, Lei*; Gan, Yingqi; Cao, Jiannong; Wang, Zhenyuhong kong polytech univ
IEEE Transactions on Mobile Computing2023-7-1DOI: 10.1109/TMC.2022.3149584
2被引10阅读
引用收藏
分享

摘要

Federated Learning (FL) has been widely used for distributed machine learning in edge computing. In FL, the model parameters are iteratively aggregated from the clients to a central server, which is inclined to be the communication bottleneck and single point of failure. To solve these drawbacks, hierarchical model training frameworks like Hierarchical Federated Learning (HFL) and E-Tree learning have been proposed. One of the most challenging problems in the hierarchical model training framework is optimizing the aggregation frequencies of the edge devices at various levels. Because, in an edge computing environment, heterogeneity in the resource can introduce synchronization delays caused by waiting for slow workers and significantly impact the training performance. This paper tackles the problem with weak synchronization where edge devices on the same level have different frequencies on local updates and/or model aggregations. Existing works based on weak synchronization lack solutions to quantitatively determine the aggregation frequencies of each edge device. Thus, we propose a resource-based aggregation frequency controlling method, termed RAF, which determines the optimal aggregation frequencies of edge devices to minimize the loss function according to heterogeneous resources. Our proposed method can alleviate the waiting time and fully utilize the resources of the edge devices. Besides, RAF dynamically adjusts the aggregation frequencies at different phases during the model training to achieve fast convergence speed and high accuracy. We evaluated the performance of RAF via extensive experiments with real datasets on our self-developed edge computing testbed. Evaluation results demonstrate that RAF outperforms the benchmark approaches in terms of learning accuracy and convergence speed.

学科与关键词

关键词
Edge intelligencedistributed machine learningaggregation frequency
相关
加载中…
  • Optimizing Training Efficiency and Cost of Hierarchical Federated Learning in Heterogeneous Mobile-Edge Cloud Computing
    Cui, Yangguang; Cao, Kun; Zhou, Junlong; Wei, Tongquan*IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023, 42(5): 1518-1531.被引 5
  • HELCFL: High-Efficiency and Low-Cost Federated Learning in Heterogeneous Mobile-Edge Computing
    Cui, Yangguang; Cao, Kun; Zhou, Junlong; Wei, Tongquan*25th Design, Automation and Test in Europe Conference and Exhibition (DATE), ELECTR NETWORK, 2022-03-14 To 2022-03-23.被引 6
  • Hierarchical Personalized Federated Learning Over Massive Mobile Edge Computing Networks
    You, Chaoqun; Guo, Kun*; Yang, Howard H.; Quek, Tony Q. S.*IEEE Transactions on Wireless Communications, 2023, 22(11): 8141-8157.被引 1
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Mobile Computing
发表日期
2023-07-01
卷期
第 22 卷, 第 7 期
页码
4181-4194
DOI
10.1109/TMC.2022.3149584
语言
ENGLISH
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61972161]; Guangdong Basic and Applied Basic Research Foundation [2020A1515011496]; Key Research and Development Program of Guangdong [2019B010154004]; Hong Kong RGC General Research Fund [PolyU 152133/18, PolyU 15217919]; Hong Kong RGC Research Impact Fund 2019/20 [R5060-19]; Hong Kong RGC Theme-based Research Scheme (TRS) [T41-603/20-R]

作者

  • Y

    Yang, Lei (通讯) (第一作者)

  • G

    Gan, Yingqi

查看全部 4 位作者收起作者
  • C

    Cao, Jiannong

    hong kong polytech univ

  • W

    Wang, Zhenyu

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417