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

页码：442 / 456

共 50 条

[1] Hierarchical federated learning based on wireless D2D networks
Liu C.-H.
Yu G.-D.
Liu S.-L.
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2023, 57 (05): : 892 - 899
[2] Federated Learning Enabled Link Scheduling in D2D Wireless Networks
Chen, Tianrui
Zhang, Xinruo
You, Minglei
Zheng, Gan
Lambotharan, Sangarapillai
IEEE WIRELESS COMMUNICATIONS LETTERS, 2024, 13 (01) : 89 - 92
[3] Decentralized Federated Learning via SGD over Wireless D2D Networks
Xing, Hong
Simeone, Osvaldo
Bi, Suzhi
PROCEEDINGS OF THE 21ST IEEE INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (IEEE SPAWC2020), 2020,
[4] Joint Scheduling and Robust Aggregation for Federated Localization Over Unreliable Wireless D2D Networks
Wu, Zheshun
Wu, Xiaoping
Long, Yunliang
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2023, 20 (03): : 3359 - 3379
[5] Cooperative D2D Partial Training for Wireless Federated Learning
Lin, Xiaohan
Liu, Yuan
Chen, Fangjiong
IEEE INTERNET OF THINGS JOURNAL, 2025, 12 (07): : 8712 - 8724
[6] Intra-cell and inter-cell interference-constrained D2D communication underlaying cellular networks
Zhang, Xuefei
Tao, Xiaofeng
Cui, Qimei
Bai, Juan
ELECTRONICS LETTERS, 2015, 51 (14) : 1117 - +
[7] Inter-Cluster Cooperation for Wireless D2D Caching Networks
Amer, Ramy
Butt, M. Majid
Bennis, Mehdi
Marchetti, Nicola
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2018, 17 (09) : 6108 - 6121
[8] Topology Learning for Heterogeneous Decentralized Federated Learning Over Unreliable D2D Networks
Wu, Zheshun
Xu, Zenglin
Zeng, Dun
Li, Junfan
Liu, Jie
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2024, 73 (08) : 12201 - 12206
[9] Decentralized Aggregation for Energy-Efficient Federated Learning via D2D Communications
Al-Abiad, Mohammed S.
Obeed, Mohanad
Hossain, Md. Jahangir
Chaaban, Anas
IEEE TRANSACTIONS ON COMMUNICATIONS, 2023, 71 (06) : 3333 - 3351
[10] Wireless Content Caching for Small Cell and D2D Networks
Gregori, Maria
Gomez-Vilardebo, Jesus
Matamoros, Javier
Gunduz, Deniz
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2016, 34 (05) : 1222 - 1234

← 1 2 3 4 5 →