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

[21] Edge Caching for D2D Enabled Hierarchical Wireless Networks with Deep Reinforcement Learning
Li, Wenkai
Wang, Chenyang
Li, Ding
Hu, Bin
Wang, Xiaofei
Ren, Jianji
WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2019, 2019
[22] Joint Coding and Scheduling Optimization in Wireless D2D Networks
Zhan, Cheng
Yao, Guo
Xiao, Fuyuan
Lai, Hong
2018 8TH INTERNATIONAL CONFERENCE ON ELECTRONICS INFORMATION AND EMERGENCY COMMUNICATION (ICEIEC), 2018, : 79 - 82
[23] Fundamental Limits of Distributed Caching in D2D Wireless Networks
Ji, Mingyue
Caire, Giuseppe
Molisch, Andreas F.
2013 IEEE INFORMATION THEORY WORKSHOP (ITW), 2013,
[24] Optimal Transport for UAV D2D Distributed Learning: Example using Federated Learning
Azmy, Sherif B.
Abutuleb, Amr
Sorour, Sameh
Zorba, Nizar
Hassanein, Hossam S.
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021), 2021,
[25] Bandwidth Allocation and Service Differentiation in D2D Wireless Networks
Baccelli, Francois
Kalamkar, Sanket S.
IEEE INFOCOM 2020 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS, 2020, : 2116 - 2125
[26] Prefix Caching for Video Streaming in Wireless D2D Networks
Hou, Hongwei
Tao, Meixia
2018 10TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP), 2018,
[27] D2D Communications Underlaying Wireless Powered Communication Networks
Wang, Haichao
Wang, Jinlong
Ding, Guoru
Han, Zhu
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2018, 67 (08) : 7872 - 7876
[28] Learning-Based Delay-Aware Caching Wireless D2D Caching Networks
Li, Yi
Zhong, Chen
Gursoy, M. Cenk
Velipasalar, Senem
IEEE ACCESS, 2018, 6 : 77250 - 77264
[29] Delay Analysis for Wireless D2D Caching with Inter-cluster Cooperation
Amer, Ramy
Butt, M. Majid
Bennis, Mehdi
Marchetti, Nicola
GLOBECOM 2017 - 2017 IEEE GLOBAL COMMUNICATIONS CONFERENCE, 2017,
[30] Minimizing Energy Consumption for Decentralized Federated Learning Using D2D Communications
Al-Abiad, Mohammed S.
Hossain, M. J.
2023 IEEE 97TH VEHICULAR TECHNOLOGY CONFERENCE, VTC2023-SPRING, 2023,

← 1 2 3 4 5 →