Graph Classification On Mnist
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| unlocking-the-potential-of-classic-gnns-for | 98.382 ± 0.095 |
| graph-transformers-without-positional | 98.362 |
| learning-long-range-dependencies-on-graphs | 98.760 ± 0.079 |
| benchmarking-graph-neural-networks | 97.340 |
| edge-augmented-graph-transformers-global-self | 98.173 |
| exphormer-sparse-transformers-for-graphs | 98.414±0.038 |
| masked-attention-is-all-you-need-for-graphs | 98.753±0.041 |
| recipe-for-a-general-powerful-scalable-graph | 98.05 |
| ckgconv-general-graph-convolution-with | 98.423 |
| topology-informed-graph-transformer | 98.230±0.133 |
| unlocking-the-potential-of-classic-gnns-for | 98.712 ± 0.137 |
| graph-inductive-biases-in-transformers | 98.108 |
| masked-attention-is-all-you-need-for-graphs | 98.917±0.020 |