Graph Property Prediction On Ogbg Code2
评估指标
Ext. data
Number of params
Test F1 score
Validation F1 score
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Ext. data | Number of params | Test F1 score | Validation F1 score |
|---|---|---|---|---|
| semi-supervised-classification-with-graph | No | 11033210 | 0.1507 ± 0.0018 | 0.1399 ± 0.0017 |
| graph-attention-networks | No | 11030210 | 0.1569 ± 0.0010 | 0.1442 ± 0.0017 |
| adaptive-filters-and-aggregator-fusion-for | No | 10986002 | 0.1595 ± 0.0019 | 0.1464 ± 0.0021 |
| structure-aware-transformer-for-graph | No | 15734000 | 0.1937 ± 0.0028 | 0.1773 ± 0.0023 |
| 模型 5 | No | 35246814 | 0.1751 ± 0.0049 | 0.1607 ± 0.0040 |
| 模型 6 | No | 63684290 | 0.1770 ± 0.0012 | 0.1631 ± 0.0090 |
| adaptive-filters-and-aggregator-fusion-for | No | 10971506 | 0.1552 ± 0.0022 | 0.1441 ± 0.0016 |
| recipe-for-a-general-powerful-scalable-graph | No | 12454066 | 0.1894 | 0.1739 ± 0.001 |
| hierarchical-graph-representation-learning | No | 10095826 | 0.1401 ± 0.0012 | 0.1405 ± 0.0012 |
| transformers-meet-directed-graphs | No | 14378069 | 0.2222 ± 0.0010 | 0.2044 ± 0.0020 |
| 模型 11 | No | 9053246 | 0.1830 ± 0.0024 | 0.1661 ± 0.0012 |
| adaptive-filters-and-aggregator-fusion-for | No | 10992050 | 0.1570 ± 0.0032 | 0.1453 ± 0.0025 |
| how-powerful-are-graph-neural-networks | No | 13841815 | 0.1581 ± 0.0026 | 0.1439 ± 0.0020 |
| 模型 14 | No | 14378069 | 0.2222 ± 0.0032 | 0.2044 ± 0.0020 |
| how-powerful-are-graph-neural-networks | No | 12390715 | 0.1495 ± 0.0023 | 0.1376 ± 0.0016 |
| adaptive-filters-and-aggregator-fusion-for | No | 11156530 | 0.1528 ± 0.0025 | 0.1427 ± 0.0020 |
| 模型 17 | No | 14952882 | 0.2018 ± 0.0021 | 0.1846 ± 0.0010 |
| 模型 18 | No | 7563746 | 0.1751 ± 0.0015 | 0.1599 ± 0.0009 |
| semi-supervised-classification-with-graph | No | 12484310 | 0.1595 ± 0.0018 | 0.1461 ± 0.0013 |
| directed-acyclic-graph-neural-networks-1 | - | - | 0.1751 ± 0.0049 | 0.1607 ± 0.0040 |
| unlocking-the-potential-of-classic-gnns-for | - | - | 0.1896 ± 0.0024 | 0.1742 ± 0.0027 |