Differentially Private Client Selection and Resource Allocation in Federated Learning for Medical Applications Using Graph Neural Networks

被引:0
|
作者
Messinis, Sotirios C. [1 ]
Protonotarios, Nicholas E. [2 ]
Doulamis, Nikolaos [1 ]
机构
[1] Natl Tech Univ Athens, Inst Commun & Comp Syst, Athens 15773, Greece
[2] Acad Athens, Math Res Ctr, Athens 11527, Greece
关键词
decentralized federated learning; resource allocation; differential privacy; client selection; graph neural networks; AGGREGATION;
D O I
10.3390/s24165142
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Federated learning (FL) has emerged as a pivotal paradigm for training machine learning models across decentralized devices while maintaining data privacy. In the healthcare domain, FL enables collaborative training among diverse medical devices and institutions, enhancing model robustness and generalizability without compromising patient privacy. In this paper, we propose DPS-GAT, a novel approach integrating graph attention networks (GATs) with differentially private client selection and resource allocation strategies in FL. Our methodology addresses the challenges of data heterogeneity and limited communication resources inherent in medical applications. By employing graph neural networks (GNNs), we effectively capture the relational structures among clients, optimizing the selection process and ensuring efficient resource distribution. Differential privacy mechanisms are incorporated, to safeguard sensitive information throughout the training process. Our extensive experiments, based on the Regensburg pediatric appendicitis open dataset, demonstrated the superiority of our approach, in terms of model accuracy, privacy preservation, and resource efficiency, compared to traditional FL methods. The ability of DPS-GAT to maintain a high and stable number of client selections across various rounds and differential privacy budgets has significant practical implications, indicating that FL systems can achieve strong privacy guarantees without compromising client engagement and model performance. This balance is essential for real-world applications where both privacy and performance are paramount. This study suggests a promising direction for more secure and efficient FL medical applications, which could improve patient care through enhanced predictive models and collaborative data utilization.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Client Selection and Resource Allocation via Graph Neural Networks for Efficient Federated Learning in Healthcare Environments
    Messinis, Sotirios C.
    Protonotarios, Nicholas E.
    Arapidis, Emmanouil
    Doulamis, Nikolaos
    17TH ACM INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS, PETRA 2024, 2024, : 606 - 612
  • [2] Joint Client Selection and Resource Allocation for Federated Learning in Mobile Edge Networks
    Luo, Long
    Cai, Qingqing
    Li, Zonghang
    Yu, Hongfang
    2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2022, : 1218 - 1223
  • [3] Joint Client Selection and Privacy Compensation for Differentially Private Federated Learning
    Xu, Ruichen
    Zhang, Ying-Jun Angela
    Huang, Jianwei
    IEEE INFOCOM 2024-IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS, INFOCOM WKSHPS 2024, 2024,
  • [4] POWER ALLOCATION FOR WIRELESS FEDERATED LEARNING USING GRAPH NEURAL NETWORKS
    Li, Boning
    Swami, Ananthram
    Segarra, Santiago
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 5243 - 5247
  • [5] Differentially Private Federated Learning With Importance Client Sampling
    Chen, Lin
    Ding, Xiaofeng
    Li, Mengqi
    Jin, Hai
    IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2024, 70 (01) : 3635 - 3649
  • [6] Client Selection with Bandwidth Allocation in Federated Learning
    Kuang, Junqian
    Yang, Miao
    Zhu, Hongbin
    Qian, Hua
    2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
  • [7] Joint client selection and resource allocation for federated edge learning with imperfect CSI
    Zhou, Sheng
    Wang, Liangmin
    Wu, Weihua
    Feng, Li
    COMPUTER NETWORKS, 2025, 257
  • [8] Device Selection and Resource Allocation for Layerwise Federated Learning in Wireless Networks
    Lee, Hyun-Suk
    IEEE SYSTEMS JOURNAL, 2022, 16 (04): : 6441 - 6444
  • [9] Towards Stagewise and Energy-Accuracy-balanced Client Selection and Resource Allocation over Dynamic Federated Learning Networks
    Wu, Minghong
    Liwang, Minghui
    Su, Yuhan
    Tang, Yuliang
    Jiao, Zhenzhen
    Wang, Xianbin
    2024 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA, ICCC, 2024,
  • [10] On the size generalizibility of graph neural networks for learning resource allocation
    Wu, Jiajun
    Sun, Chengjian
    Yang, Chenyang
    SCIENCE CHINA-INFORMATION SCIENCES, 2024, 67 (04)