{"ID":2869833,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18171","arxiv_id":"2509.18171","title":"FedIA: Towards Domain-Robust Aggregation in Federated Graph Learning","abstract":"Federated Graph Learning (FGL) enables a central server to coordinate model training across distributed clients without local graph data being shared. However, FGL significantly suffers from cross-silo domain shifts, where each \"silo\" (domain) contains a limited number of clients with distinct graph topologies. These heterogeneities induce divergent optimization trajectories, ultimately leading to global model divergence. In this work, we reveal a severe architectural pathology termed Structural Orthogonality: the topology-dependent message passing mechanism forces gradients from different domains to target disjoint coordinates in the parameter space. Through a controlled comparison between backbones, we statistically prove that GNN updates are near-perpendicular across domains (with projection ratios $\\to$ 0). Consequently, naive averaging leads to Consensus Collapse, a phenomenon where sparse, informative structural signals from individual domains are diluted by the near-zero updates of others. This forces the global model into a \"sub-optimal\" state that fails to represent domain-specific structural patterns, resulting in poor generalization. To address this, we propose FedIA, a lightweight server-side framework designed to reconcile update conflicts without auxiliary communication. FedIA operates in two stages: (1) Global Importance Masking (GIM) identifies a shared parameter subspace to filter out domain-specific structural noise and prevent signal dilution; (2) Confidence-Aware Momentum Weighting (CAM) dynamically re-weights client contributions based on gradient reliability to amplify stable optimization signals.","short_abstract":"Federated Graph Learning (FGL) enables a central server to coordinate model training across distributed clients without local graph data being shared. However, FGL significantly suffers from cross-silo domain shifts, where each \"silo\" (domain) contains a limited number of clients with distinct graph topologies. These h...","url_abs":"https://arxiv.org/abs/2509.18171","url_pdf":"https://arxiv.org/pdf/2509.18171v3","authors":"[\"Zhanting Zhou\",\"KaHou Tam\",\"Yiding Feng\",\"Ziqiang Zheng\",\"Zeyu Ma\",\"Yang Yang\"]","published":"2025-09-17T13:04:11Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false}