Node Classification On Pubmed Full Supervised
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| GraphSAGE | 87.1% | Inductive Representation Learning on Large Graphs | |
| FDGATII | 90.3524% | FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping | |
| ASGCN | 90.6% | Adaptive Sampling Towards Fast Graph Representation Learning | |
| 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+DropEdge | 91.70% | DropEdge: Towards Deep Graph Convolutional Networks on Node Classification |
0 of 7 row(s) selected.