FedSST: Rethinking Fair Federated Graph Learning under Structural Shift

Federated Graph Learning (FGL) offers a privacypreserving paradigm for collaborative training on graph data, yet significant topological heterogeneity poses a critical threat to generalization fairness, often yielding a global model dominated by a subset of clients. This introduces two critical issues: at the global level, aggregation bias disproportionately amplifies the influence of dominant clients with lower structural complexity, while at the local level, blind optimization results in inefficient and inequitable training processes. To address these challenges, we propose FedSST, a structure-aware adaptive optimization framework. FedSST introduces a fair, structure-based signal to quantify client contributions, which in turn guides fair aggregation and adaptive local training. Extensive experiments across diverse cross-domain benchmarks demonstrate that FedSST significantly outperforms state-of-the-art methods in both generalization fairness and overall performance.