Graph Personalized Federated Learning via Client Network Learning

Abstract

Graph classification is a widely studied problem for applications such as molecule/protein function prediction and drug discovery. Powerful graph neural networks (GNNs) have demonstrated state-of-the-art performance for the classification of complex graphs, but training such models can require significant amounts of high-quality labeled graphs that are expensive to collect. When individual institutes do not possess sufficient graph data, federated learning (FL) becomes a handy solution for them to collaboratively obtain powerful graph models without directly sharing their own graph data. However, existing FL frameworks for graph data do not consider the realistic setting of personalized FL with heterogeneous data, where each client aims to leverage the data of certain other clients to boost its own model performance. In this work, inspired by graph structure learning, we propose to learn a dynamic client network that tracks the graph data similarity across clients to guide model sharing along FL. Specifically, we rely on the marginal parameters of local GNNs to dynamically learn the client network, and refer to a set of fundamental graph properties to guide its learning. Extensive experiments on three real-world graph datasets demonstrate the consistent effectiveness of our two major proposed modules, which also mutually verify the effectiveness of each other.