Research map / Graph learning / GNN architectures
Federated Graph Classification over Non-IID Graphs
Han Xie, Jing Ma, Li Xiong, Carl Yang
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 |
|---|---|---|---|
| cluster clients by gradients (GCFL) instead of FedAvg | GIN federated · NCI1 (30 clients) | average accuracy: 0.6474 -> 0.7326 | Improved |
| use gradient-sequence DTW clustering (GCFL+) instead of last-gradient clustering (GCFL) | GCFL · NCI1 (30 clients) | average accuracy: 0.7326 -> 0.7422 | Improved |
| use GCFL+ instead of GCFL | GCFL · PROTEINS (10 clients) | average accuracy: 0.7739 -> 0.7776 | Improved |
| use GCFL+ instead of GCFL | GCFL · IMDB-BINARY (10 clients) | average accuracy: 0.8256 -> 0.8299 | Improved |
| use GCFL+ instead of GCFL | GCFL · MOLECULES | average accuracy: 0.7661 -> 0.7745 | Improved |
| use GCFL+ instead of GCFL | GCFL · BIOCHEM | average accuracy: 0.7172 -> 0.7312 | Improved |
| use GCFL+ instead of GCFL | GCFL · MIX | average accuracy: 0.7056 -> 0.7121 | Improved |
| apply FedAvg instead of local training | GIN · MIX (13 clients) | average accuracy: 0.7001 -> 0.6886 | Hurt |
| apply FedAvg instead of local training | GIN · NCI1 (30 clients) | average accuracy: 0.6468 -> 0.6474 | No clear effect |
| standardize the gradient-norm series in GCFL+ (ablation) | GCFL+ · single and multi dataset | performance gain | No clear effect |
| vary clustering thresholds epsilon1 and epsilon2 within feasible ranges (ablation) | GCFL/GCFL+ · MOLECULES | average accuracy | No clear effect |
Closest papers by meaning
- Federated Graph-Level Clustering Network (AAAI 2025 · similarity 0.91)
- Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective (ICML 2025 · similarity 0.89)
- 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)
- Modeling Inter-Intra Heterogeneity for Graph Federated Learning (AAAI 2025 · similarity 0.88)
- Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement (NeurIPS 2025 · similarity 0.88)
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.
