Institute of Communication and Computer Systems, National Technical University of Athens, 15773 Athens, Greece.
Mathematics Research Center, Academy of Athens, 11527 Athens, Greece.
Sensors (Basel). 2024 Aug 8;24(16):5142. doi: 10.3390/s24165142.
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.
联邦学习（FL）已经成为一种重要的范例，可以在保护数据隐私的同时，在分散的设备上训练机器学习模型。在医疗保健领域，FL 可以实现不同医疗设备和机构之间的协作训练，提高模型的稳健性和泛化能力，同时不损害患者的隐私。在本文中，我们提出了 DPS-GAT，这是一种将图注意网络（GAT）与 FL 中的差分隐私客户端选择和资源分配策略相结合的新方法。我们的方法解决了医疗应用中固有的数据异质性和有限通信资源的挑战。通过使用图神经网络（GNN），我们有效地捕捉了客户端之间的关系结构，优化了选择过程，并确保了有效的资源分配。差分隐私机制被纳入其中，以在整个训练过程中保护敏感信息。我们基于雷根斯堡儿科阑尾炎开放数据集进行了广泛的实验，结果表明，与传统的 FL 方法相比，我们的方法在模型准确性、隐私保护和资源效率方面具有优越性。DPS-GAT 能够在各种轮次和差分隐私预算下保持较高且稳定的客户端选择数量，这具有重要的实际意义，表明 FL 系统可以在不影响客户端参与和模型性能的情况下实现强大的隐私保护。这种平衡对于隐私和性能都至关重要的实际应用非常重要。本研究为更安全、更高效的 FL 医疗应用提供了一个有前途的方向，通过增强预测模型和协作数据利用，可以改善患者的护理。
