ASFGNN: Automated separated-federated graph neural network

• Published in: Peer-to-peer networking and applications Vol. 14; no. 3; pp. 1692 - 1704
• Main Authors: Zheng, Longfei, Zhou, Jun, Chen, Chaochao, Wu, Bingzhe, Wang, Li, Zhang, Benyu
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2021; Springer Nature B.V
• Subjects: Automation; Clients; Communications Engineering; Computer Communication Networks; Engineering; Graph neural networks; Information Systems and Communication Service; Learning; Mathematical models; Message passing; Networks; Neural networks; Optimization; Optimization techniques; Parameters; Signal,Image and Speech Processing; Special Issue on Privacy-Preserving Computing; Training; Tuning; Federated learning; Privacy preserving; Bayesian optimization; Graph neural network
• DOI: 10.1007/s12083-021-01074-w
• ISSN: 1936-6442

Graph Neural Networks (GNNs) have achieved remarkable performance by taking advantage of graph data. The success of GNN models always depends on rich features and adjacent relationships. However, in practice, such data are usually isolated by different data owners (clients) and thus are likely to be Non-Independent and Identically Distributed (Non-IID). Meanwhile, considering the limited network status of data owners, hyper-parameters optimization for collaborative learning approaches is time-consuming in data isolation scenarios. To address these problems, we propose an Automated Separated-Federated Graph Neural Network (ASFGNN) learning paradigm. ASFGNN consists of two main components, i.e., the training of GNN and the tuning of hyper-parameters. Specifically, to solve the data Non-IID problem, we first propose a separated-federated GNN learning model, which decouples the training of GNN into two parts: the message passing part that is done by clients separately, and the loss computing part that is learnt by clients federally. To handle the time-consuming parameter tuning problem, we leverage Bayesian optimization technique to automatically tune the hyper-parameters of all the clients. We conduct experiments on benchmark datasets and the results demonstrate that ASFGNN significantly outperforms the naive federated GNN, in terms of both accuracy and parameter-tuning efficiency.