Graph Regression On Zinc Full
Metriken
Test MAE
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Test MAE |
|---|---|
| how-powerful-are-graph-neural-networks | 0.068±0.004 |
| towards-a-practical-k-dimensional-weisfeiler | 0.045±0.006 |
| masked-attention-is-all-you-need-for-graphs | 0.0109±0.0002 |
| pure-transformers-are-powerful-graph-learners | 0.047±0.010 |
| towards-a-practical-k-dimensional-weisfeiler | 0.042±0.003 |
| masked-attention-is-all-you-need-for-graphs | 0.0154±0.0001 |
| graph-inductive-biases-in-transformers | 0.023 |
| recipe-for-a-general-powerful-scalable-graph | 0.024±0.007 |
| do-transformers-really-perform-bad-for-graph | 0.036±0.002 |
| semi-supervised-classification-with-graph | 0.152±0.023 |
| masked-attention-is-all-you-need-for-graphs | 0.017±0.001 |
| principal-neighbourhood-aggregation-for-graph | 0.057±0.007 |
| topology-informed-graph-transformer | 0.014 |
| how-attentive-are-graph-attention-networks | 0.079±0.004 |
| graph-attention-networks | 0.078±0.006 |
| masked-attention-is-all-you-need-for-graphs | 0.0122±0.0004 |
| sign-and-basis-invariant-networks-for | 0.024±0.003 |
| inductive-representation-learning-on-large | 0.126±0.003 |
| masked-attention-is-all-you-need-for-graphs | 0.027±0.001 |