Research map / Graph learning / Graph self-supervised learning
Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning
Wentao Yu, Sheng Wan, Shuo Chen, Bo Han, Chen Gong
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 |
|---|---|---|---|
| add semantic knowledge sharing (ablation) | FedSSA · Cora and Tolokers | accuracy | Improved |
| add structural knowledge sharing (ablation) | FedSSA · Cora and Tolokers | accuracy | Improved |
| add both semantic and structural knowledge sharing (ablation) | FedSSA · Cora | accuracy: more than 5% | Improved |
| use FedSSA instead of second-best FedIIH | FedSSA · heterophilic datasets | average accuracy: 2.82% | Improved |
| use FedSSA instead of FedIIH on homophilic average | FedSSA · six homophilic datasets | average accuracy: 83.10 -> 83.53 | Improved |
| use FedSSA instead of FedIIH on heterophilic average | FedSSA · five heterophilic datasets | average accuracy/AUC: 64.52 -> 67.34 | Improved |
| use FedSSA instead of FedIIH | FedSSA · Minesweeper (10 clients) | AUC: 73.23 -> 82.16 | Improved |
| add semantic and structural knowledge sharing for faster convergence | FedSSA · non-overlapping, 10 clients | communication rounds to converge: 90 -> 60 | Improved |
| vary K_node, K_struct, lambda_1, lambda_2 (ablation) | FedSSA · Cora | accuracy | No clear effect |
| use FedSSA instead of Local training on Amazon-ratings | FedSSA · Amazon-ratings (10 clients) | accuracy: 45.89 -> 45.11 | No clear effect |
Closest papers by meaning
- Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective (ICML 2025 · similarity 0.91)
- FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity (CVPR 2025 · similarity 0.91)
- Modeling Inter-Intra Heterogeneity for Graph Federated Learning (AAAI 2025 · similarity 0.91)
- $S^2$FGL: Spatial Spectral Federated Graph Learning (ICML 2025 · similarity 0.91)
- FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference (NeurIPS 2024 · similarity 0.91)
- Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement (NeurIPS 2025 · similarity 0.90)
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.
