Hierarchically Federated Learning in Wireless Networks: D2D Consensus and Inter-Cell Aggregation

被引：0
|
作者：
Zhang, Jie [1 ]
Chen, Li [1 ]
Chen, Yunfei [2 ]
Chen, Xiaohui [1 ]
Wei, Guo [1 ]
机构：
[1] University of Science and Technology of China, CAS Key Laboratory of Wireless Optical Communication, Hefei,230027, China
[2] University of Durham, Department of Engineering, Durham,DH1 3LE, United Kingdom
来源：
IEEE Transactions on Machine Learning in Communications and Networking | 2024年 / 2卷
关键词：
Decentralized federated learning (DFL) architecture enables clients to collaboratively train a shared machine learning model without a central parameter server. However; it is difficult to apply DFL to a multi-cell scenario due to inadequate model averaging and cross-cell device-to-device (D2D) communications. In this paper; we propose a hierarchically decentralized federated learning (HDFL) framework that combines intra-cell D2D links between devices and backhaul communications between base stations. In HDFL; devices from different cells collaboratively train a global model using periodic intra-cell D2D consensus and inter-cell aggregation. The strong convergence guarantee of the proposed HDFL algorithm is established even for non-convex objectives. Based on the convergence analysis; we characterize the network topology of each cell; the communication interval of intra-cell consensus and inter-cell aggregation on the training performance. To further improve the performance of HDFL; we optimize the computation capacity selection and bandwidth allocation to minimize the training latency and energy overhead. Numerical results based on the MNIST and CIFAR-10 datasets validate the superiority of HDFL over traditional DFL methods in the multi-cell scenario. © 2023 CCBY;
D O I：
10.1109/TMLCN.2024.3385355
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：442 / 456
相关论文
共 50 条
  • [41] An Analytical Model of the Small World Effect in D2D Wireless Networks
    Ilyas, Muhammad U.
    Khan, Muhammad Murtaza
    Radha, Hayder
    Al-Ghamdi, Ahmed
    Munshi, Asmaa
    IEEE ACCESS, 2019, 7 : 35661 - 35672
  • [42] An Efficient Distributed Machine Learning Framework in Wireless D2D Networks: Convergence Analysis and System Implementation
    Cheng, Kun
    Guo, Fengxian
    Peng, Mugen
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (05) : 6723 - 6738
  • [43] Q-Learning based Edge Caching Optimization for D2D Enabled Hierarchical Wireless Networks
    Wang, Chenyang
    Wang, Shanjia
    Li, Ding
    Wang, Xiaofei
    Li, Xiuhua
    Leung, Victor C. M.
    2018 IEEE 15TH INTERNATIONAL CONFERENCE ON MOBILE AD HOC AND SENSOR SYSTEMS (MASS), 2018, : 55 - 63
  • [44] Load balancing in D2D networks Using Reinforcement Learning
    Barros, Pedro H.
    Cardoso-Pereira, Isadora
    Foschini, Luca
    Corradi, Antonio
    Ramos, Heitor S.
    2019 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS (ISCC), 2019, : 316 - 321
  • [45] Connectivity-Aware Semi-Decentralized Federated Learning over Time-Varying D2D Networks
    Parasnis, Rohit
    Hosseinalipour, Seyyedali
    Chu, Yun-Wei
    Chiang, Mung
    Brinton, Christopher G.
    PROCEEDINGS OF THE 2023 INTERNATIONAL SYMPOSIUM ON THEORY, ALGORITHMIC FOUNDATIONS, AND PROTOCOL DESIGN FOR MOBILE NETWORKS AND MOBILE COMPUTING, MOBIHOC 2023, 2023, : 31 - 40
  • [46] Multi-Level Over-the-Air Aggregation of Mobile Edge Computing Over D2D Wireless Networks
    Wang, Feng
    Lau, Vincent K. N.
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2022, 21 (10) : 8337 - 8353
  • [47] Semi-Decentralized Federated Learning With Cooperative D2D Local Model Aggregations
    Lin, Frank Po-Chen
    Hosseinalipour, Seyyedali
    Azam, Sheikh Shams
    Brinton, Christopher G.
    Michelusi, Nicolo
    IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2021, 39 (12) : 3851 - 3869
  • [48] Layer-wise Efficient Federated Learning with Distributed Clustering and D2D Communications
    Sun, Chen
    Liu, Xiangnan
    Huang, Xinyu
    Fischione, Carlo
    2024 IEEE 25TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS, SPAWC 2024, 2024, : 831 - 835
  • [49] D2D Relay Management in Multi-cell Networks
    Deng, Junquan
    Tirkkonen, Olav
    Chen, Tao
    2017 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2017,
  • [50] Caching D2D Connections in Small-Cell Networks
    Zhao, Nan
    Liu, Xiaonan
    Chen, Yunfei
    Zhang, Shun
    Li, Zan
    Chen, Bingcai
    Alouini, Mohamed-Slim
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2018, 67 (12) : 12326 - 12338
12345