Node Classification On Europe Air Traffic
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| GCN_cheby (Kipf and Welling, 2017) | 46.0 | Semi-Supervised Classification with Graph Convolutional Networks | - |
| UGT | 56.92 ±6.36 | Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity | - |
| DEMO-Net(weight) | 45.9 | DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification | - |
| Intersection (Li et al., 2018) | 44.3 | Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | - |
| GAT (Velickovic et al., 2018) | 42.4 | Graph Attention Networks | - |
| GraphSAGE (Hamilton et al., [2017a]) | 27.2 | Inductive Representation Learning on Large Graphs | - |
| GCN (Kipf and Welling, 2017) | 37.1 | Semi-Supervised Classification with Graph Convolutional Networks | - |
0 of 7 row(s) selected.