Command Palette
Search for a command to run...
Graph Property Prediction On Ogbg Molpcba
Metrics
Ext. data
Number of params
Test AP
Validation AP
Results
Performance results of various models on this benchmark
| Paper Title | Repository | |||||
|---|---|---|---|---|---|---|
| HyperFusion | No | 10887085 | 0.3204 ± 0.0001 | 0.3353 ± 0.0002 | - | - |
| HyperFusino | No | 10887085 | 0.3204 ± 0.0001 | 0.3353 ± 0.0002 | - | - |
| TGT-Ag+TGT-At-DP | Yes | 47000000 | 0.3167 ± 0.0031 | - | Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers | |
| HIG(pre-trained on PCQM4M) | Yes | 119529665 | 0.3167 ± 0.0034 | 0.3252 ± 0.0043 | - | - |
| Graphormer | - | 119529664 | 0.3140 ± 0.0032 | 0.3227 ± 0.0024 | Do Transformers Really Perform Bad for Graph Representation? | |
| Graphormer (pre-trained on PCQM4M) | Yes | 119529664 | 0.3140 ± 0.0032 | 0.3227 ± 0.0024 | Do Transformers Really Perform Bad for Graph Representation? | |
| GatedGCN-HSG | - | - | 0.3129±0.0020 | - | Next Level Message-Passing with Hierarchical Support Graphs | |
| No | 3842048 | 0.3031 ± 0.0026 | 0.3115 ± 0.0020 | Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering | ||
| PAS | No | 5560960 | 0.3012 ± 0.0039 | 0.3151 ± 0.0047 | - | - |
| Nested GIN+virtual node (ensemble) | No | 44187480 | 0.3007 ± 0.0037 | 0.3059 ± 0.0056 | Nested Graph Neural Networks | |
| Nested GIN+virtual node (ens) | - | - | 0.3007 ± 0.0037 | 0.3059 ± 0.0056 | Nested Graph Neural Networks | |
| GINE+bot | No | 5511680 | 0.2994 ± 0.0019 | 0.3094 ± 0.0023 | - | - |
| CRaWl | No | 6115728 | 0.2986 ± 0.0025 | 0.3075 ± 0.0020 | Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing | |
| GatedGCN+ | No | 6016860 | 0.2981 ± 0.0024 | 0.3011 ± 0.0037 | Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence | |
| GINE+ w/ APPNP | No | 6147029 | 0.2979 ± 0.0030 | 0.3126 ± 0.0023 | Graph convolutions that can finally model local structure | |
| EGT | - | - | 0.2961 ± 0.0024 | - | Global Self-Attention as a Replacement for Graph Convolution | |
| PHC-GNN | No | 1690328 | 0.2947 ± 0.0026 | 0.3068 ± 0.0025 | Parameterized Hypercomplex Graph Neural Networks for Graph Classification | |
| GIN-AK | No | 3081029 | 0.2930 ± 0.0044 | 0.3047 ± 0.0007 | From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness | |
| GINE+ w/ virtual nodes | No | 6147029 | 0.2917 ± 0.0015 | 0.3065 ± 0.0030 | Graph convolutions that can finally model local structure | |
| GPS | No | 9744496 | 0.2907 | 0.3015 ± 0.0038 | Recipe for a General, Powerful, Scalable Graph Transformer |
0 of 36 row(s) selected.