Graph Classification On Re M5K
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| GFN-light | 49.75% | Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification | - |
| DGK | 41.27% | Deep Graph Kernels | - |
| WEGL | 55.1% | Wasserstein Embedding for Graph Learning | - |
| 2D CNN | 52.11% | Graph Classification with 2D Convolutional Neural Networks | - |
| GFN | 49.43% | Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification | - |
| GIN-0 | 57.5% | How Powerful are Graph Neural Networks? | - |
| CapsGNN | 52.88% | Capsule Graph Neural Network | |
| GAT-GC (f-Scaled) | 57.22% | Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation | - |
0 of 8 row(s) selected.