Research map / Graph learning / Graph self-supervised learning
Federated Graph Learning via Structure-Aware Fusion Using a Kalman Framework with Learnable Dynamics
Bisheng Tang, Xiaojun Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use Fed-Kalter instead of FedStar across 1 to 4 domain settings | federated graph classification · 1-4 domain settings | average accuracy: 5.56%, 2.57%, 1.00%, and 1.46% over FedStar | Improved |
| use Fed-Kalter instead of FedVN across 1 to 4 domain settings | federated graph classification · 1-4 domain settings | average accuracy: 3.95%, 2.58%, 0.82%, and 0.68% | Improved |
| use Fed-Kalter instead of FedAvg | federated graph classification · One-domain average | accuracy: 70.23 -> 74.65 | Improved |
| use Fed-Kalter instead of FedAvg | federated graph classification · Four-domain CHEM-BIO-SN-CV | accuracy: 66.75 -> 73.69 | Improved |
| use federated training (FedAvg) instead of local-only training | graph classification · Four-domain CHEM-BIO-SN-CV | accuracy: 71.37 -> 66.75 | Hurt |
| use Fed-Kalter instead of local-only training | graph classification · Four-domain CHEM-BIO-SN-CV | accuracy: 71.37 -> 73.69 | Improved |
| use Fed-Kalter instead of FedSage on computer vision graphs | federated graph classification · One-domain CV | accuracy: 85.78 -> 85.38 | No clear effect |
| use Fed-Kalter instead of FedStar on social networks | federated graph classification · One-domain SN | accuracy: 63.68 -> 68.14 | Improved |
Closest papers by meaning
- FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference (NeurIPS 2024 · similarity 0.89)
- Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective (ICML 2025 · similarity 0.88)
- Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning (AAAI 2025 · similarity 0.88)
- $S^2$FGL: Spatial Spectral Federated Graph Learning (ICML 2025 · similarity 0.88)
- FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity (CVPR 2025 · similarity 0.87)
- Federated Graph Learning under Domain Shift with Generalizable Prototypes (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
