Graph Regression On Pgr
Métriques
R2
RMSE
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | R2 | RMSE |
|---|---|---|
| graph-attention-networks | 0.681±0.000 | 0.546±0.681 |
| semi-supervised-classification-with-graph | 0.658±0.000 | 0.565±0.658 |
| do-transformers-really-perform-bad-for-graph | OOM | OOM |
| how-attentive-are-graph-attention-networks | 0.666±0.000 | 0.558±0.666 |
| dropgnn-random-dropouts-increase-the | 0.702±0.000 | 0.527±0.702 |
| masked-attention-is-all-you-need-for-graphs | 0.725±0.000 | 0.507±0.725 |
| how-powerful-are-graph-neural-networks | 0.696±0.000 | 0.532±0.696 |
| principal-neighbourhood-aggregation-for-graph | 0.717±0.000 | 0.514±0.717 |
| pure-transformers-are-powerful-graph-learners | 0.684±0.000 | 0.543±0.684 |