Graph Regression On Kit
Metriken
R2
RMSE
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | R2 | RMSE |
|---|---|---|
| how-attentive-are-graph-attention-networks | 0.826±0.000 | 0.453±0.826 |
| dropgnn-random-dropouts-increase-the | 0.835±0.000 | 0.441±0.835 |
| pure-transformers-are-powerful-graph-learners | 0.800±0.000 | 0.486±0.800 |
| semi-supervised-classification-with-graph | 0.814±0.000 | 0.469±0.814 |
| do-transformers-really-perform-bad-for-graph | OOM | OOM |
| principal-neighbourhood-aggregation-for-graph | 0.843±0.000 | 0.430±0.843 |
| graph-attention-networks | 0.833±0.000 | 0.443±0.833 |
| how-powerful-are-graph-neural-networks | 0.833±0.000 | 0.444±0.833 |
| masked-attention-is-all-you-need-for-graphs | 0.841±0.000 | 0.433±0.841 |