Graph Regression On Esr2
المقاييس
R2
RMSE
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
اسم النموذج | R2 | RMSE | Paper Title | Repository |
|---|---|---|---|---|
| GAT | 0.666±0.000 | 0.510±0.666 | Graph Attention Networks | |
| DropGIN | 0.675±0.000 | 0.503±0.675 | DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks | |
| ESA (Edge set attention, no positional encodings) | 0.697±0.000 | 0.486±0.697 | An end-to-end attention-based approach for learning on graphs | - |
| GCN | 0.642±0.000 | 0.528±0.642 | Semi-Supervised Classification with Graph Convolutional Networks | |
| GATv2 | 0.655±0.000 | 0.518±0.655 | How Attentive are Graph Attention Networks? | |
| GIN | 0.668±0.000 | 0.509±0.668 | How Powerful are Graph Neural Networks? | |
| PNA | 0.696±0.000 | 0.486±0.696 | Principal Neighbourhood Aggregation for Graph Nets | |
| TokenGT | 0.641±0.000 | 0.529±0.641 | Pure Transformers are Powerful Graph Learners | |
| Graphormer | OOM | OOM | Do Transformers Really Perform Bad for Graph Representation? |
0 of 9 row(s) selected.