Low-Latency Federated Learning via Dynamic Model Partitioning for Healthcare IoT

被引:2
作者
He, Peng [1 ,2 ,3 ]
Lan, Chunhui [1 ,2 ,3 ]
Bashir, Ali Kashif [4 ]
Wu, Dapeng [1 ,2 ,3 ]
Wang, Ruyan [1 ,2 ,3 ]
Kharel, Rupak [5 ]
Yu, Keping [6 ]
机构
[1] Chongqing Univ Posts & Telecommun, Sch Commun & Informat Engn, Chongqing 400065, Peoples R China
[2] Chongqing Univ Posts & Telecommun, Intelligent Connect Technol Key Lab Chongqing Educ, Adv Network, Chongqing, Chin, Myanmar
[3] Chongqing Univ Posts & Telecommun, Chongqing Key Lab Ubiquitous Sensing & Networking, Chongqing 400065, Peoples R China
[4] Manchester Metropolitan Univ, Dept Comp & Math, Manchester M15 6BH, England
[5] Univ Huddersfield, Sch Comp & Engn, Huddersfield HD1 3DH, England
[6] Hosei Univ, Grad Sch Sci & Engn, Tokyo 1848584, Japan
关键词
Federated learning; split learning; medical data privacy; Lyapunov optimization; PRIVACY;
D O I
10.1109/JBHI.2023.3298446
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Federated learning (FL) is receiving much attention in the Healthcare Internet of Things (H-IoT) to support various instantaneous E-health services. Today, the deployment of FL suffers from several challenges, such as high training latency and data privacy leakage risks, especially for resource-constrained medical devices. In this article, we develop a three-layer FL architecture to decrease training latency by introducing split learning into FL. We formulate a long-term optimization problem to minimize the local model training latency while preserving the privacy of the original medical data in H-IoT. Specially, a Privacy-ware Model Partitioning Algorithm (PMPA) is proposed to solve the formulated problem based on the Lyapunov optimization theory. In PMPA, the local model is partitioned properly between a resource-constrained medical end device and an edge server, which meets privacy requirements and energy consumption constraints. The proposed PMPA is separated into two phases. In the first phase, a partition point set is obtained using Kullback-Leibler (KL) divergence to meet the privacy requirement. In the second phase, we employ the model partitioning function, derived through Lyapunov optimization, to select the partition point from the partition point set that that satisfies the energy consumption constraints. Simulation results show that compared with traditional FL, the proposed algorithm can significantly reduce the local training latency. Moreover, the proposed algorithm improves the efficiency of medical image classification while ensuring medical data security.
引用
收藏
页码:4684 / 4695
页数:12
相关论文
共 50 条
  • [31] MODEL: A Model Poisoning Defense Framework for Federated Learning via Truth Discovery
    Wu, Minzhe
    Zhao, Bowen
    Xiao, Yang
    Deng, Congjian
    Liu, Yuan
    Liu, Ximeng
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 8747 - 8759
  • [32] Secrecy Driven Federated Learning via Cooperative Jamming: An Approach of Latency Minimization
    Wang, Tianshun
    Li, Yang
    Wu, Yuan
    Quek, Tony Q. S.
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2022, 10 (04) : 1687 - 1703
  • [33] Boosted federated learning based on improved Particle Swarm Optimization for healthcare IoT devices
    Houssein, Essam H.
    Sayed, Awny
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 163
  • [34] Federated Reinforcement Learning-Supported IDS for IoT-steered Healthcare Systems
    Otoum, Safa
    Guizani, Nadra
    Mouftah, Hussein
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021), 2021,
  • [35] A blockchain-based federated learning mechanism for privacy preservation of healthcare IoT data
    Moulahi, Wided
    Jdey, Imen
    Moulahi, Tarek
    Alawida, Moatsum
    Alabdulatif, Abdulatif
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 167
  • [36] Lightweight and Dynamic Privacy-Preserving Federated Learning via Functional Encryption
    Yu, Boan
    Zhao, Jun
    Zhang, Kai
    Gong, Junqing
    Qian, Haifeng
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2025, 20 : 2496 - 2508
  • [37] An Adaptive Federated Learning Approach for Efficiency and Privacy Preservation of Dynamic Network of IoT
    Dave, Madhavi
    Bhatt, Dulari
    Mundanad, Manjari
    SMART TRENDS IN COMPUTING AND COMMUNICATIONS, VOL 2, SMARTCOM 2024, 2024, 946 : 301 - 310
  • [38] Botnet Detection and Mitigation Model for IoT Networks Using Federated Learning
    Filho, Francisco Lopes de Caldas
    Soares, Samuel Carlos Meneses
    Oroski, Elder
    Albuquerque, Robson de Oliveira
    da Mata, Rafael Zerbini Alves
    de Mendonca, Fabio Lucio Lopes
    de Sousa Jr, Rafael Timoteo
    SENSORS, 2023, 23 (14)
  • [39] FedMCCS: Multicriteria Client Selection Model for Optimal IoT Federated Learning
    AbdulRahman, Sawsan
    Tout, Hanine
    Mourad, Azzam
    Talhi, Chamseddine
    IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (06) : 4723 - 4735
  • [40] Leveraging Transfer Learning Domain Adaptation Model With Federated Learning to Revolutionise Healthcare
    Verma, Priyanka
    Bharot, Nitesh
    Breslin, John G.
    O'Shea, Donna
    Mishra, Anand Kumar
    Vidyarthi, Ankit
    Gupta, Deepak
    EXPERT SYSTEMS, 2025, 42 (02)