Graph Regression On Parp1
Métriques
R2
RMSE
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | R2 | RMSE |
|---|---|---|
| semi-supervised-classification-with-graph | 0.912±0.000 | 0.372±0.912 |
| do-transformers-really-perform-bad-for-graph | OOM | OOM |
| pure-transformers-are-powerful-graph-learners | 0.907±0.000 | 0.383±0.907 |
| principal-neighbourhood-aggregation-for-graph | 0.924±0.000 | 0.346±0.924 |
| graph-attention-networks | 0.921±0.000 | 0.353±0.921 |
| masked-attention-is-all-you-need-for-graphs | 0.925±0.000 | 0.343±0.925 |
| how-attentive-are-graph-attention-networks | 0.919±0.000 | 0.356±0.919 |
| how-powerful-are-graph-neural-networks | 0.922±0.000 | 0.349±0.922 |
| dropgnn-random-dropouts-increase-the | 0.920±0.000 | 0.354±0.920 |