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
  • [21] Unsupervised Resource Allocation with Graph Neural Networks
    Cranmer, Miles
    Melchior, Peter
    Nord, Brian
    NEURIPS 2020 WORKSHOP ON PRE-REGISTRATION IN MACHINE LEARNING, VOL 148, 2020, 148 : 272 - 284
  • [22] Client selection and resource scheduling in reliable federated learning for UAV-assisted vehicular networks
    Zhao, Hongbo
    Geng, Liwei
    Feng, Wenquan
    Zhou, Changming
    CHINESE JOURNAL OF AERONAUTICS, 2024, 37 (09) : 328 - 346
  • [23] Client selection and resource scheduling in reliable federated learning for UAV-assisted vehicular networks
    Hongbo ZHAO
    Liwei GENG
    Wenquan FENG
    Changming ZHOU
    Chinese Journal of Aeronautics, 2024, 37 (09) : 328 - 346
  • [24] Joint Client and Cross-Client Edge Selection for Cost-Efficient Federated Learning of Graph Convolutional Networks
    Huang, Guangjing
    Chen, Xu
    Wu, Qiong
    Li, Jingyi
    Huang, Qianyi
    IEEE-ACM TRANSACTIONS ON NETWORKING, 2024,
  • [25] Differentially Private Federated Learning for Anomaly Detection in eHealth Networks
    Cholakoska, Ana
    Pfitzner, Bjarne
    Gjoreski, Hristijan
    Rakovic, Valentin
    Arnrich, Bert
    Kalendar, Marija
    UBICOMP/ISWC '21 ADJUNCT: PROCEEDINGS OF THE 2021 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2021 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, 2021, : 514 - 518
  • [26] Differentially Private Graph Neural Networks for Whole-Graph Classification
    Mueller, Tamara T.
    Paetzold, Johannes C.
    Prabhakar, Chinmay
    Usynin, Dmitrii
    Rueckert, Daniel
    Kaissis, Georgios
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (06) : 7308 - 7318
  • [27] Client Selection and Bandwidth Allocation for Federated Learning: An Online Optimization Perspective
    Ji, Yun
    Kou, Zhoubin
    Zhong, Xiaoxiong
    Li, Hangfan
    Yang, Fan
    Zhang, Sheng
    2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 5075 - 5080
  • [28] Differentially Private Medical Texts Generation Using Generative Neural Networks
    Al Aziz, Md Momin
    Ahmed, Tanbir
    Faequa, Tasnia
    Jiang, Xiaoqian
    Yao, Yiyu
    Mohammed, Noman
    ACM Transactions on Computing for Healthcare, 2022, 3 (01):
  • [29] GraphCS: Graph-based client selection for heterogeneity in federated learning
    Chang, Tao
    Li, Li
    Wu, MeiHan
    Yu, Wei
    Wang, Xiaodong
    Xu, ChengZhong
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2023, 177 : 131 - 143
  • [30] Optimizing Federated Learning Using Remote Embeddings for Graph Neural Networks
    Naman, Pranjal
    Simmhan, Yogesh
    EURO-PAR 2024: PARALLEL PROCESSING, PART II, EURO-PAR 2024, 2024, 14802 : 470 - 484