Link Property Prediction On Ogbl Collab
Metrics
Ext. data
Number of params
Test Hits@50
Validation Hits@50
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Ext. data | Number of params | Test Hits@50 | Validation Hits@50 |
|---|---|---|---|---|
| reconsidering-the-performance-of-gae-in-link | No | 126669825 | 0.6816 ± 0.0041 | 1.0000 ± 0.0000 |
| on-the-effect-of-the-average-clustering | No | 0 | 0.5050 ± 0.0000 | 0.6098 ± 0.0000 |
| edge2node-reducing-edge-prediction-to-node | No | 526851 | 0.9515 ± 0.1410 | 0.9546 ± 0.1270 |
| semi-supervised-classification-with-graph | No | 296449 | 0.4714 ± 0.0145 | 0.5263 ± 0.0115 |
| revisiting-graph-neural-networks-for-link-1 | No | 501570 | 0.6474 ± 0.0043 | 0.6495 ± 0.0043 |
| inductive-representation-learning-on-large | No | 460289 | 0.5463 ± 0.0112 | 0.5688 ± 0.0077 |
| Model 7 | No | 483363845 | 0.6792 ± 0.0074 | 0.6771 ± 0.0083 |
| from-graph-low-rank-global-attention-to-2-fwl | No | 35200656 | 0.6909 ± 0.0055 | 1.0000 ± 0.0000 |
| Model 9 | No | 3284065 | 0.6636 ± 0.5876 | 0.6631 ± 0.0021 |
| Model 10 | No | 1184867 | 0.6572 ± 0.0053 | 0.6621 ± 0.0016 |
| deepergcn-all-you-need-to-train-deeper-gcns | No | 117383 | 0.5273 ± 0.0047 | 0.6187 ± 0.0045 |
| pairwise-learning-for-neural-link-prediction | No | 35112192 | 0.6872 ± 0.0052 | 1.0000 ± 0.0000 |
| Model 13 | No | 0 | 0.6417 ± 0.0000 | 0.6349 ± 0.0000 |
| Model 14 | No | 30191104 | 0.7012 ± 0.0016 | 1.0000 ± 0.0000 |
| open-graph-benchmark-datasets-for-machine | No | 60514049 | 0.3886 ± 0.0029 | 0.4896 ± 0.0029 |
| Model 16 | No | 1064446212 | 0.7129 ± 0.0018 | 0.7385 ± 0.0099 |
| edge-proposal-sets-for-link-prediction | No | 0 | 0.6548 ± 0.0000 | 0.9735 ± 0.0000 |
| network-in-graph-neural-network | No | 428033 | 0.5348 ± 0.0040 | 0.6273 ± 0.0040 |
| inductive-representation-learning-on-large | No | 460289 | 0.4810 ± 0.0081 | 0.5688 ± 0.0077 |
| network-in-graph-neural-network | No | 591873 | 0.5359 ± 0.0056 | 0.6281 ± 0.0046 |
| vq-gnn-a-universal-framework-to-scale-up | - | - | 0.4316 ± 0.0134 | - |
| Model 22 | No | 34980864 | 0.7087 ± 0.0033 | 1.0000 ± 0.0000 |
| gidn-a-lightweight-graph-inception-diffusion | No | 60449025 | 0.7096 ± 0.0055 | 0.9620 ± 0.0040 |
| vq-gnn-a-universal-framework-to-scale-up | - | - | 0.4673 ± 0.0164 . | - |
| simplifying-subgraph-representation-learning | No | 5913025 | 0.6683 ± 0.0030 | 0.9861 ± 0.0006 |
| inductive-representation-learning-on-large | - | 460289 | - | - |
| deepwalk-online-learning-of-social | No | 61390187 | 0.5037 ± 0.0034 | Please tell us |
| semi-supervised-classification-with-graph | No | 296449 | 0.4475 ± 0.0107 | 0.5263 ± 0.0115 |
| pairwise-learning-for-neural-link-prediction | No | 34980864 | 0.7059 ± 0.0029 | 1.0000 ± 0.0000 |
| revisiting-graph-neural-networks-for-link-1 | No | 501570 | 0.5471 ± 0.0049 | 0.6495 ± 0.0043 |
| node2vec-scalable-feature-learning-for | No | 30322945 | 0.4888 ± 0.0054 | 0.5703 ± 0.0052 |
| from-graph-low-rank-global-attention-to-2-fwl | No | 1069489 | 0.5221 ± 0.0072 | 0.6088 ± 0.0059 |
| vq-gnn-a-universal-framework-to-scale-up | - | - | 0.4102 ± 0.0099 | - |
| Model 34 | No | 0 | 0.6137 ± 0.0000 | 0.6036 ± 0.0000 |