Node Classification On Pattern 100K
Métriques
Accuracy (%)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy (%) | Paper Title | Repository |
|---|---|---|---|
| DGN | 86.680 | Directional Graph Networks | - |
| GraphSage | 50.516 | Inductive Representation Learning on Large Graphs | - |
| EGT | 86.816 | Global Self-Attention as a Replacement for Graph Convolution | - |
| PNA | 86.567 | Principal Neighbourhood Aggregation for Graph Nets | - |
| FactorGCN | 86.57 ± 0.02 | Factorizable Graph Convolutional Networks | - |
| GatedGCN | 84.480 | Residual Gated Graph ConvNets | - |
| GAT | 75.824 | Graph Attention Networks | - |
| GIN | 85.590 | How Powerful are Graph Neural Networks? | - |
| MoNet | 85.482 | Geometric deep learning on graphs and manifolds using mixture model CNNs | - |
0 of 9 row(s) selected.