Node Classification On Pokec
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| finding-global-homophily-in-graph-neural | 83.05±0.07 |
| classic-gnns-are-strong-baselines-reassessing | 86.33 ± 0.17 |
| polynormer-polynomial-expressive-graph | 86.10±0.05 |
| learning-long-range-dependencies-on-graphs | 86.46 ± 0.09 |
| graph-neural-networks-with-learnable-and | 82.83±0.04 |
| feature-selection-key-to-enhance-node | 81.55±0.09 |
| large-scale-learning-on-non-homophilous | 82.04±0.07 |