Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.18171 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915747695951872 |
|---|---|
| author | Zhou, Zhanting Tam, KaHou Feng, Yiding Zheng, Ziqiang Ma, Zeyu Yang, Yang |
| author_facet | Zhou, Zhanting Tam, KaHou Feng, Yiding Zheng, Ziqiang Ma, Zeyu Yang, Yang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18171 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedIA: Towards Domain-Robust Aggregation in Federated Graph Learning Zhou, Zhanting Tam, KaHou Feng, Yiding Zheng, Ziqiang Ma, Zeyu Yang, Yang Machine Learning 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. |
| title | FedIA: Towards Domain-Robust Aggregation in Federated Graph Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.18171 |