Graph Regression On Pgr
Métriques
R2
RMSE
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | R2 | RMSE | Paper Title | Repository |
|---|---|---|---|---|
| GAT | 0.681±0.000 | 0.546±0.681 | Graph Attention Networks | |
| GCN | 0.658±0.000 | 0.565±0.658 | Semi-Supervised Classification with Graph Convolutional Networks | |
| Graphormer | OOM | OOM | Do Transformers Really Perform Bad for Graph Representation? | |
| GATv2 | 0.666±0.000 | 0.558±0.666 | How Attentive are Graph Attention Networks? | |
| GINDrop | 0.702±0.000 | 0.527±0.702 | DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks | |
| ESA (Edge set attention, no positional encodings) | 0.725±0.000 | 0.507±0.725 | An end-to-end attention-based approach for learning on graphs | - |
| GIN | 0.696±0.000 | 0.532±0.696 | How Powerful are Graph Neural Networks? | |
| PNA | 0.717±0.000 | 0.514±0.717 | Principal Neighbourhood Aggregation for Graph Nets | |
| TokenGT | 0.684±0.000 | 0.543±0.684 | Pure Transformers are Powerful Graph Learners |
0 of 9 row(s) selected.