Vertical Federated Learning Over Cloud-RAN: Convergence Analysis and System Optimization

被引:3
|
作者
Shi, Yuanming [1 ]
Xia, Shuhao [1 ]
Zhou, Yong [1 ]
Mao, Yijie [1 ]
Jiang, Chunxiao [2 ,3 ]
Tao, Meixia [4 ]
机构
[1] ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
[2] Tsinghua Univ, Tsinghua Space Ctr, Beijing 100084, Peoples R China
[3] Tsinghua Univ, Beijing Natl Res Ctr Informat Sci & Technol, Beijing 100084, Peoples R China
[4] Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 201210, Peoples R China
基金
中国国家自然科学基金;
关键词
Servers; Wireless communication; Atmospheric modeling; Training; Data models; Optimization; Computational modeling; Vertical federated learning; cloud radio access network; over-the-air computation; C-RAN; DESIGN;
D O I
10.1109/TWC.2023.3288122
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Vertical federated learning (FL) is a collaborative machine learning framework that enables devices to learn a global model from the feature-partition datasets without sharing local raw data. However, as the number of the local intermediate outputs is proportional to the training samples, it is critical to develop communication-efficient techniques for wireless vertical FL to support high-dimensional model aggregation with full device participation. In this paper, we propose a novel cloud radio access network (Cloud-RAN) based vertical FL system to enable fast and accurate model aggregation by leveraging over-the-air computation (AirComp) and alleviating communication straggler issue with cooperative model aggregation among geographically distributed edge servers. However, the model aggregation error caused by AirComp and quantization errors caused by the limited fronthaul capacity degrade the learning performance for vertical FL. To address these issues, we characterize the convergence behavior of the vertical FL algorithm considering both uplink and downlink transmissions. To improve the learning performance, we establish a system optimization framework by joint transceiver and fronthaul quantization design, for which successive convex approximation and alternate convex search based system optimization algorithms are developed. We conduct extensive simulations to demonstrate the effectiveness of the proposed system architecture and optimization framework for vertical FL.
引用
收藏
页码:1327 / 1342
页数:16
相关论文
共 50 条
  • [1] Green Federated Learning Over Cloud-RAN With Limited Fronthaul Capacity and Quantized Neural Networks
    Wang, Jiali
    Mao, Yijie
    Wang, Ting
    Shi, Yuanming
    [J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (05) : 4300 - 4314
  • [2] Employing MEC in the Cloud-RAN: An Experimental Analysis
    Makris, Nikos
    Passas, Virgilios
    Korakis, Thanasis
    Tassiulas, Leandros
    [J]. EDGETECH'18: PROCEEDINGS OF THE 2018 TECHNOLOGIES FOR THE WIRELESS EDGE WORKSHOP, 2018, : 15 - 19
  • [3] Collaborative Edge AI Inference Over Cloud-RAN
    Zhang, Pengfei
    Wen, Dingzhu
    Zhu, Guangxu
    Chen, Qimei
    Han, Kaifeng
    Shi, Yuanming
    [J]. IEEE TRANSACTIONS ON COMMUNICATIONS, 2024, 72 (09) : 5641 - 5656
  • [4] Computation Offloading in Cloud-RAN Based Mobile Cloud Computing System
    Cheng, Jinkun
    Shi, Yuanming
    Bai, Bo
    Chen, Wei
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2016,
  • [5] Analysis of Handover Performance Improvement in Cloud-RAN Architecture
    Liu, Liang
    Yang, Feng
    Wang, Richard
    Shi, Zhenning
    Stidwell, Alan
    Gu, Daqing
    [J]. 2012 7TH INTERNATIONAL ICST CONFERENCE ON COMMUNICATIONS AND NETWORKING IN CHINA (CHINACOM), 2012, : 850 - 855
  • [6] Performance Analysis of VNFs for Sizing Cloud-RAN Infrastructures
    Rodriguez, Veronica Quintuna
    Guillemin, Fabrice
    [J]. 2017 IEEE CONFERENCE ON NETWORK FUNCTION VIRTUALIZATION AND SOFTWARE DEFINED NETWORKS (NFV-SDN), 2017, : 98 - 103
  • [7] Convergence Analysis and System Design for Federated Learning Over Wireless Networks
    Wan, Shuo
    Lu, Jiaxun
    Fan, Pingyi
    Shao, Yunfeng
    Peng, Chenghui
    Letaief, Khaled B.
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2021, 39 (12) : 3622 - 3639
  • [8] Convergence Analysis and Optimization of Over-the-Air Federated Meta-Learning
    Wang, Yuxin
    Zheng, Jingheng
    Ni, Wanli
    Tian, Hui
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS, ICC WORKSHOPS, 2023, : 379 - 384
  • [9] A Green Video Control Plane with Fixed-Mobile Convergence and Cloud-RAN
    Aparicio-Pardo, Ramon
    Sassatelli, Lucile
    [J]. 2017 PROCEEDINGS OF THE 29TH INTERNATIONAL TELETRAFFIC CONGRESS (ITC 29), VOL 1, 2017, : 28 - 36
  • [10] Performance Evaluation of Cloud-RAN System with Carrier Frequency Offset
    Li, Jian
    Chen, Dageng
    Wang, Yi
    Wu, Jianjun
    [J]. 2012 IEEE GLOBECOM WORKSHOPS (GC WKSHPS), 2012, : 222 - 226