Graph Property Prediction On Ogbg Molhiv
المقاييس
Test ROC-AUC
Validation ROC-AUC
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Test ROC-AUC | Validation ROC-AUC |
|---|---|---|
| nested-graph-neural-networks | 0.7986 ± 0.0105 | 0.8080 ± 0.0278 |
| edge-augmented-graph-transformers-global-self | 0.806 ± 0.0065 | - |
| graph-propagation-transformer-for-graph | 0.8126 ± 0.0032 | - |
| النموذج 4 | 0.7825 ± 0.0121 | 0.8009 ± 0.0078 |
| النموذج 5 | 0.8208 ± 0.0037 | 0.8036 ± 0.0059 |
| unlocking-the-potential-of-classic-gnns-for | 0.8040 ± 0.0164 | 0.8329 ± 0.0158 |
| flag-adversarial-data-augmentation-for-graph-1 | 0.7683 ± 0.0102 | 0.8176 ± 0.0087 |
| generalizing-topological-graph-neural | 0.7944 ± 1.40 | - |
| graphnorm-a-principled-approach-to | 0.7883 ± 0.0100 | 0.7904 ± 0.0115 |
| deepergcn-all-you-need-to-train-deeper-gcns | 0.7858 ± 0.0117 | 0.8427 ± 0.0063 |
| how-powerful-are-graph-neural-networks | 0.7707 ± 0.0149 | 0.8479 ± 0.0068 |
| weisfeiler-and-lehman-go-cellular-cw-networks | 0.8094 ± 0.0057 | 0.8277 ± 0.0099 |
| النموذج 13 | 0.8060 ± 0.0010 | 0.8420 ± 0.0030 |
| principal-neighbourhood-aggregation-for-graph | 0.7905 ± 0.0132 | 0.8519 ± 0.0099 |
| flag-adversarial-data-augmentation-for-graph-1 | 0.7942 ± 0.0120 | 0.8425 ± 0.0061 |
| nested-graph-neural-networks | 0.7834 ± 0.0186 | 0.8317 ± 0.0199 |
| weisfeiler-and-lehman-go-cellular-cw-networks | 0.8055 ± 0.0104 | 0.8310 ± 0.0102 |
| directional-graph-networks-1 | 0.7970 ± 0.0097 | 0.8470 ± 0.0047 |
| do-transformers-really-perform-bad-for-graph | 0.8051 ± 0.0053 | 0.8310 ± 0.0089 |
| hierarchical-inter-message-passing-for | 0.7880 ± 0.0082 | Please tell us |
| النموذج 21 | 0.8244 ± 0.0033 | 0.8329 ± 0.0039 |
| semi-supervised-classification-with-graph | 0.7549 ± 0.0163 | 0.8042 ± 0.0107 |
| flag-adversarial-data-augmentation-for-graph-1 | 0.7748 ± 0.0096 | 0.8438 ± 0.0128 |
| adaptive-filters-and-aggregator-fusion-for | 0.7721 ± 0.0110 | 0.8366 ± 0.0074 |
| interpretable-and-generalizable-graph | 0.8067 ± 0.0950 | 0.8347 ± 0.0031 |
| النموذج 26 | 0.8420 ± 0.0015 | 0.8238 ± 0.0028 |
| how-powerful-are-graph-neural-networks | 0.7558 ± 0.0140 | 0.8232 ± 0.0090 |
| improving-graph-neural-network-expressivity | 0.7799 ± 0.0100 | 0.8658 ± 0.0084 |
| robust-deep-auc-maximization-a-new-surrogate | 0.8352 ± 0.0054 | 0.8238 ± 0.0061 |
| molecular-representation-learning-by | 0.8232 ± 0.0047 | 0.8331 ± 0.0054 |
| النموذج 31 | 0.8403 ± 0.0021 | 0.8176 ± 0.0034 |
| flag-adversarial-data-augmentation-for-graph-1 | 0.7654 ± 0.0114 | 0.8225 ± 0.0155 |
| improving-graph-neural-network-expressivity | 0.8039 ± 0.0090 | 0.8473 ± 0.0096 |
| النموذج 34 | 0.8475 ± 0.0003 | 0.8275 ± 0.0008 |
| wasserstein-embedding-for-graph-learning | 0.7757 ± 0.0111 | 0.8101 ± 0.0097 |
| do-transformers-really-perform-bad-for-graph | 0.8225 ± 0.0001 | 0.8396 ± 0.0001 |
| do-transformers-really-perform-bad-for-graph | 0.8051 ± 0.0053 | 0.8310 ± 0.0089 |
| parameterized-hypercomplex-graph-neural | 0.7934 ± 0.0116 | 0.8217 ± 0.0089 |
| adaptive-filters-and-aggregator-fusion-for | 0.7818 ± 0.0153 | 0.8396 ± 0.0097 |
| recipe-for-a-general-powerful-scalable-graph | 0.7880 | 0.8255 ± 0.0092 |
| semi-supervised-classification-with-graph | 0.7599 ± 0.0119 | 0.8384 ± 0.0091 |
| semi-supervised-classification-with-graph | 0.7606 ± 0.0097 | 0.8204 ± 0.0141 |
| a-persistent-weisfeilerlehman-procedure-for | 0.8039 ± 0.0040 | 0.8279 ± 0.0059 |