Trustworthy Federated Graph Learning Framework for Wireless Internet of Things

Abstract

As computational power has increased rapidly in recent years, deep learning techniques have found widespread use in wireless internet of things (IoT) networks, where they have shown remarkable results. In order to make the most of the data contained in graphs and their surrounding contexts, graph intelligence has seen extensive use in a wide variety of tailored wireless applications. However, the sensitive nature of client data poses serious challenges to conventional customization approaches, which depend on centralized graph learning on globe graphs. In this work, we introduce federated graph learning, dubbed FGL, that is capable of producing accurate personalization while still protecting clients' anonymity. To train graph intelligence models jointly based on distributed graphs inferred from local data, we employ a trustworthy model updating technique. In order to make use of graph knowledge beyond the scope of dynamic interplay, we present a trustworthy graph extension mechanism for incorporating high-level knowledge while yet maintaining confidentiality. Six customization datasets were used to show that with excellent trustworthy protection, FGL achieves 2.0% to 5.0% lower errors than the state-of-the-art federated customization approaches. For ethical and insightful personalization, FGL offers a potential path forward for mining distributed graph data.