Graph Regression On F2
Metrics
R2
RMSE
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | R2 | RMSE |
|---|---|---|
| pure-transformers-are-powerful-graph-learners | 0.872±0.000 | 0.363±0.872 |
| do-transformers-really-perform-bad-for-graph | OOM | OOM |
| semi-supervised-classification-with-graph | 0.878±0.000 | 0.355±0.878 |
| how-powerful-are-graph-neural-networks | 0.887±0.000 | 0.342±0.887 |
| masked-attention-is-all-you-need-for-graphs | 0.891±0.000 | 0.335±0.891 |
| principal-neighbourhood-aggregation-for-graph | 0.891±0.000 | 0.336±0.891 |
| dropgnn-random-dropouts-increase-the | 0.886±0.000 | 0.343±0.886 |
| graph-attention-networks | 0.886±0.000 | 0.343±0.886 |
| how-attentive-are-graph-attention-networks | 0.885±0.000 | 0.344±0.885 |