Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysis

תקציר מקורי באנגליתarXiv:2509.18171v5 Announce Type: replace Abstract: Federated graph learning (FGL) trains a shared graph model across clients whose local graphs differ in node features, labels, and connectivity while keeping raw graph data decentralized. Although graph-domain shifts across clients can severely degrade the global model, existing FGL approaches for graph-domain shift mainly adapt local representations, propagation, or graph-derived collaboration, while the server typically applies the same aggregation rule to every parameter coordinate. In this work, we analyze how graph-domain shifts affect server-side aggregation. We find that, as clients optimize under distinct graph-domain conditions, they gradually concentrate their strongest updates on different parameter coordinates, making important