Graph Regression On Parp1
Métriques
R2
RMSE
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | R2 | RMSE | Paper Title | Repository |
|---|---|---|---|---|
| GCN | 0.912±0.000 | 0.372±0.912 | Semi-Supervised Classification with Graph Convolutional Networks | |
| Graphormer | OOM | OOM | Do Transformers Really Perform Bad for Graph Representation? | |
| TokenGT | 0.907±0.000 | 0.383±0.907 | Pure Transformers are Powerful Graph Learners | |
| PNA | 0.924±0.000 | 0.346±0.924 | Principal Neighbourhood Aggregation for Graph Nets | |
| GAT | 0.921±0.000 | 0.353±0.921 | Graph Attention Networks | |
| ESA (Edge set attention, no positional encodings) | 0.925±0.000 | 0.343±0.925 | An end-to-end attention-based approach for learning on graphs | - |
| GATv2 | 0.919±0.000 | 0.356±0.919 | How Attentive are Graph Attention Networks? | |
| GIN | 0.922±0.000 | 0.349±0.922 | How Powerful are Graph Neural Networks? | |
| DropGIN | 0.920±0.000 | 0.354±0.920 | DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks |
0 of 9 row(s) selected.