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

[11] Federated Learning Beyond the Star: Local D2D Model Consensus with Global Cluster Sampling
Lin, Frank Po-Chen
Hosseinalipour, Seyyedali
Azam, Sheikh Shams
Brinton, Christopher G.
Michelusi, Nicolo
2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
[12] Inter-cell coordination in wireless data networks
Bonald, Thomas
Borst, Sem
Proutiere, Alexandre
EUROPEAN TRANSACTIONS ON TELECOMMUNICATIONS, 2006, 17 (03): : 303 - 312
[13] Decentralized Aggregation for Energy-Efficient Federated Learning via Overlapped Clustering and D2D Communications
The School of Engineering, The University of British Columbia, Kelowna
BC
V1V 1V7, Canada
arXiv, 1600,
[14] A Ring Topology-based Communication-Efficient Scheme for D2D Wireless Federated Learning
Xu, Zimu
Tian, Wei
Liu, Yingxin
Ning, Wanjun
Wu, Jingjin
IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 2820 - 2825
[15] Green and Cooperative DASH in Wireless D2D Networks
Zhang, Lin
Zhang, Xiaoyi
Qu, Kaiming
Ren, Luming
Deng, Jie
Zhu, Konglin
WIRELESS PERSONAL COMMUNICATIONS, 2015, 84 (03) : 1797 - 1816
[16] Fundamental Limits of Caching in Wireless D2D Networks
Ji, Mingyue
Caire, Giuseppe
Molisch, Andreas F.
IEEE TRANSACTIONS ON INFORMATION THEORY, 2016, 62 (02) : 849 - 869
[17] Green and Cooperative DASH in Wireless D2D Networks
Lin Zhang
Xiaoyi Zhang
Kaiming Qu
Luming Ren
Jie Deng
Konglin Zhu
Wireless Personal Communications, 2015, 84 : 1797 - 1816
[18] Receiver-Centric Inter-Cell Interference Cancellation in D2D-Assisted Networks
Rose, Luca
Maso, Marco
2016 IEEE GLOBECOM WORKSHOPS (GC WKSHPS), 2016,
[19] Learning to Cooperate in D2D Caching Networks
Paschos, Georgios S.
Destounis, Apostolos
Iosifidis, George
2019 IEEE 20TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC 2019), 2019,
[20] A Reinforcement Learning Approach for D2D Spectrum Sharing in Wireless Industrial URLLC Networks
Sanusi, Idayat O.
Nasr, Karim M.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2024, 21 (05): : 5410 - 5419

← 1 2 3 4 5 →