Graph Property Prediction On Ogbg Ppa
Métriques
Ext. data
Number of params
Test Accuracy
Validation Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Ext. data | Number of params | Test Accuracy | Validation Accuracy |
|---|---|---|---|---|
| breaking-the-expressive-bottlenecks-of-graph-1 | No | 1369397 | 0.7976 ± 0.0072 | 0.7518 ± 0.0080 |
| semi-supervised-classification-with-graph | No | 479437 | 0.6839 ± 0.0084 | 0.6497 ± 0.0034 |
| unlocking-the-potential-of-classic-gnns-for | No | 5547557 | 0.8258 ± 0.0055 | 0.7815 ± 0.0043 |
| unlocking-the-potential-of-classic-gnns-for | No | 5549605 | 0.8077 ± 0.0041 | 0.7586 ± 0.0032 |
| Modèle 5 | No | 4006704 | 0.7432 ± 0.0033 | 0.6989 ± 0.0037 |
| deepergcn-all-you-need-to-train-deeper-gcns | No | 2336421 | 0.7712 ± 0.0071 | 0.7313 ± 0.0078 |
| how-powerful-are-graph-neural-networks | No | 3288042 | 0.7037 ± 0.0107 | 0.6678 ± 0.0105 |
| flag-adversarial-data-augmentation-for-graph-1 | No | 2336421 | 0.7752 ± 0.0069 | 0.7484 ± 0.0052 |
| flag-adversarial-data-augmentation-for-graph-1 | No | 1836942 | 0.6905 ± 0.0092 | 0.6465 ± 0.0070 |
| Modèle 10 | No | 16346166 | 0.8201 ± 0.0019 | 0.7720 ± 0.0023 |
| unlocking-the-potential-of-classic-gnns-for | No | 8173605 | 0.8107 ± 0.0053 | 0.7786 ± 0.0095 |
| Modèle 12 | No | 3717160 | 0.7828 ± 0.0024 | 0.7523 ± 0.0028 |
| flag-adversarial-data-augmentation-for-graph-1 | No | 1930537 | 0.6944 ± 0.0052 | 0.6638 ± 0.0055 |
| flag-adversarial-data-augmentation-for-graph-1 | No | 3288042 | 0.7245 ± 0.0114 | 0.6789 ± 0.0079 |
| how-powerful-are-graph-neural-networks | No | 1836942 | 0.6892 ± 0.0100 | 0.6562 ± 0.0107 |
| Modèle 16 | No | 3758642 | 0.8140 ± 0.0028 | 0.7811 ± 0.0012 |
| semi-supervised-classification-with-graph | No | 1930537 | 0.6857 ± 0.0061 | 0.6511 ± 0.0048 |
| recipe-for-a-general-powerful-scalable-graph | No | 3434533 | 0.8015 | 0.7556 ± 0.0027 |