Link Property Prediction On Ogbl Ddi
評価指標
Ext. data
Number of params
Test Hits@20
Validation Hits@20
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Ext. data | Number of params | Test Hits@20 | Validation Hits@20 | Paper Title | Repository |
|---|---|---|---|---|---|---|
| ELGNN | No | 10512391 | 0.9777 ± 0.0037 | 0.8965 ± 0.0021 | Ensemble Learning for Graph Neural Networks | |
| Refined-GAE | No | 13816833 | 0.9443 ± 0.0057 | 0.7979 ± 0.0159 | Reconsidering the Performance of GAE in Link Prediction | |
| Node2vec | No | 645249 | 0.2326 ± 0.0209 | 0.3292 ± 0.0121 | node2vec: Scalable Feature Learning for Networks | |
| NGNN + GraphSAGE | No | 1618433 | 0.5770 ± 0.1523 | 0.7323 ± 0.0040 | Network In Graph Neural Network | - |
| GraphSAGE + Edge Attr | No | 3761665 | 0.8781 ± 0.0474 | 0.8044 ± 0.0404 | - | - |
| BUDDY | No | 2712931 | 0.7654 ± 0.0459 | 0.6927 ± 0.0054 | - | - |
| SEAL | No | 531138 | 0.3056 ± 0.0386 | 0.2849 ± 0.0269 | Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning | |
| GCN+JKNet | No | 1421571 | 0.6056 ± 0.0869 | 0.6776 ± 0.0095 | Semi-Supervised Classification with Graph Convolutional Networks | |
| GIDN@YITU | No | 3506691 | 0.9542 ± 0.0000 | 0.8258 ± 0.0000 | GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction | - |
| NGNN + GCN | No | 1487361 | 0.5483 ± 0.1581 | 0.7121 ± 0.0038 | Network In Graph Neural Network | - |
| HyperFusion | No | 976022023 | 0.9972 ± 0.0004 | 0.9956 ± 0.0001 | - | - |
| GraphSAGE | No | 1421057 | 0.5390 ± 0.0474 | 0.6262 ± 0.0037 | Inductive Representation Learning on Large Graphs | |
| NeuralCommonNeighbor | No | 1412098 | 0.8232 ± 0.0610 | 0.7172 ± 0.0025 | Neural Common Neighbor with Completion for Link Prediction | |
| GCN | No | 1289985 | 0.3707 ± 0.0507 | 0.5550 ± 0.0208 | Semi-Supervised Classification with Graph Convolutional Networks | |
| MAD Learning | No | 1228897 | 0.6781 ± 0.0294 | 0.7010 ± 0.0082 | Memory-Associated Differential Learning | |
| Common Neighbor | No | 0 | 0.1773 ± 0.0000 | 0.0947 ± 0.0000 | - | - |
| GCN (node embedding) | No | 5125250 | 0.9549 ± 0.0073 | 0.9098 ± 0.0294 | Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods | - |
| DeepWalk | No | 1543913 | 0.2246 ± 0.0290 | Please tell us | DeepWalk: Online Learning of Social Representations | |
| GraphSAGE+anchor distance | No | 3760134 | 0.8239 ± 0.0437 | 0.8206 ± 0.0298 | Distance-Enhanced Graph Neural Network for Link Prediction | |
| GDNN | No | 3761665 | 0.9037 ± 0.0193 | 0.8599 ± 0.0286 | - | - |
0 of 31 row(s) selected.