Graph Regression On Pcqm4M Lsc
Metrics
Test MAE
Validation MAE
Results
Performance results of various models on this benchmark
Model Name | Test MAE | Validation MAE | Paper Title | Repository |
|---|---|---|---|---|
| MLP-fingerprint | 20.68 | 0.2044 | OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs | |
| Higher-Order Transformer | - | 0.1263 | Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs | |
| EGT | - | 0.1224 | Global Self-Attention as a Replacement for Graph Convolution | |
| GCN-Virtual | 15.79 | 0.1536 | OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs | |
| GCN | 18.38 | 0.1684 | OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs | |
| Graphormer | 13.28 | 0.1234 | Do Transformers Really Perform Bad for Graph Representation? | |
| GPTrans-L | - | 0.1151 | Graph Propagation Transformer for Graph Representation Learning | |
| O-GNN | - | 0.1148 | O-GNN: Incorporating Ring Priors into Molecular Modeling | |
| Graphormer + GFSA | - | 0.1193 | Graph Convolutions Enrich the Self-Attention in Transformers! | |
| GIN-virtual | 14.87 | 0.1396 | OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs | |
| GIN | 16.78 | - | OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs |
0 of 11 row(s) selected.