Node Classification On Usa Air Traffic
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Planetoid* | 64.7 | Revisiting Semi-Supervised Learning with Graph Embeddings | |
| Union (Li et al., 2018) | 58.2 | Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | |
| UGT | 66.22±4.55 | Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity | |
| GraphSAGE (Hamilton et al., [2017a]) | 31.6 | Inductive Representation Learning on Large Graphs | |
| DEMO-Net(weight) | 64.7 | DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification | |
| Intersection (Li et al., 2018) | 57.3 | Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | |
| GAT (Velickovic et al., 2018) | 58.5 | Graph Attention Networks |
0 of 7 row(s) selected.