Node Classification On Pubmed Full Supervised
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| GraphSAGE+DropEdge | 91.70% | DropEdge: Towards Deep Graph Convolutional Networks on Node Classification |
| ASGCN | 90.6% | Adaptive Sampling Towards Fast Graph Representation Learning |
| FDGATII | 90.3524% | FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping |
| GCNII* | 90.30% | Simple and Deep Graph Convolutional Networks |
| Graph ESN | 89.2±0.3 | Beyond Homophily with Graph Echo State Networks |
| FastGCN | 88.00% | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling |
| GraphSAGE | 87.1% | Inductive Representation Learning on Large Graphs |
0 of 7 row(s) selected.