Graph Regression On Pcqm4Mv2 Lsc
Metrics
Test MAE
Validation MAE
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Test MAE | Validation MAE |
|---|---|---|
| edge-augmented-graph-transformers-global-self | 0.0862 | 0.0857 |
| graph-propagation-transformer-for-graph | 0.0821 | 0.0809 |
| recipe-for-a-general-powerful-scalable-graph | 0.0862 | 0.0852 |
| topology-informed-graph-transformer | - | 0.0826 |
| graph-convolutions-enrich-the-self-attention | - | 0.0860 |
| do-transformers-really-perform-bad-for-graph | - | 0.0864 |
| the-information-pathways-hypothesis | - | 0.0865 |
| semi-supervised-classification-with-graph | 0.1398 | 0.1379 |
| masked-attention-is-all-you-need-for-graphs | N/A | 0.0235 |
| ogb-lsc-a-large-scale-challenge-for-machine | 0.1760 | 0.1753 |
| graph-inductive-biases-in-transformers | - | 0.0859 |
| highly-accurate-quantum-chemical-property | 0.0705 | 0.0693 |
| graph-self-attention-for-learning-graph | 0.0876 | 0.0867 |
| pure-transformers-are-powerful-graph-learners | 0.0919 | 0.0910 |
| edge-augmented-graph-transformers-global-self | 0.0683 | 0.0671 |
| triplet-interaction-improves-graph | 0.0683 | 0.0671 |
| how-powerful-are-graph-neural-networks | 0.1218 | 0.1195 |
| graph-propagation-transformer-for-graph | 0.0842 | 0.0833 |
| one-transformer-can-understand-both-2d-3d | 0.0782 | 0.0772 |
| the-information-pathways-hypothesis | - | 0.0876 |