FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity

Federated Graph Learning (FGL) has emerged as a solution to address real-world privacy concerns and data silos in graph learning, which relies on Graph Neural Networks (GNNs).Nevertheless, the homophily level discrepancies within the local graph data of clients, termed homophily heterogeneity, significantly degrade the generalizability of a global GNN. Existing research ignores this issue and suffers from unpromising collaboration. In this paper, we propose $\textbf{FedSPA}$, an effective hyperparameter-free framework that addresses homophily heterogeneity from the perspectives of homophily conflict and homophily bias, concepts that have yet to be defined or explored.In the first place, the homophily conflict arises when training on inconsistent homophily levels across clients. Correspondingly, we propose $\textbf{S}$ubgraph Feature $\textbf{P}$ropagation Decoupling (SFPD), thereby achieving collaboration on unified homophily levels across clients. To further address homophily bias, we design Homophily Bias-Driven $\textbf{A}$ggregation (HBDA) which emphasizes clients with lower biases. It enables the adaptive adjustment of each client contribution to the global GNN based on its homophily bias. The superiority of $\textbf{FedSPA}$ is validated through extensive experiments.