Node Classification On Brazil Air Traffic
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| UGT | 0.8 ± 0.05 | Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity | |
| Intersection (Li et al., 2018) | 0.459 | Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | |
| GraphSAGE (Hamilton et al., [2017a]) | 0.404 | Inductive Representation Learning on Large Graphs | |
| DEMO-Net(weight) | 0.543 ± 0.034 | DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification | |
| GAT (Velickovic et al., 2018) | 0.382 | Graph Attention Networks | |
| GCN_cheby (Kipf and Welling, 2017) | 0.516 | Semi-Supervised Classification with Graph Convolutional Networks | |
| Union (Li et al., 2018) | 0.466 | Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning |
0 of 7 row(s) selected.