| []() | | No | 0.9972 ± 0.0004 | 0.9956 ± 0.0001 | 976022023 | HyperFusion | |
| Ensemble Learning for Graph Neural Networks | ✓ Link | No | 0.9777 ± 0.0037 | 0.8965 ± 0.0021 | 10512391 | ELGNN | 2023-10-22 |
| Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods | ✓ Link | No | 0.9549 ± 0.0073 | 0.9098 ± 0.0294 | 5125250 | GCN (node embedding) | 2024-11-22 |
| GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction | | No | 0.9542 ± 0.0000 | 0.8258 ± 0.0000 | 3506691 | GIDN@YITU | 2022-10-04 |
| Adaptive Graph Diffusion Networks | ✓ Link | No | 0.9538 ± 0.0094 | 0.8943 ± 0.0281 | 3506691 | AGDN (AUC loss) | 2020-12-30 |
| Reconsidering the Performance of GAE in Link Prediction | ✓ Link | No | 0.9443 ± 0.0057 | 0.7979 ± 0.0159 | 13816833 | Refined-GAE | 2024-11-06 |
| Path-aware Siamese Graph Neural Network for Link Prediction | ✓ Link | No | 0.9284 ± 0.0047 | 0.8306 ± 0.0134 | 3499009 | PSG | 2022-08-10 |
| Pairwise Learning for Neural Link Prediction | ✓ Link | No | 0.9088 ± 0.0313 | 0.8242 ± 0.0253 | 3497473 | PLNLP | 2021-12-06 |
| []() | | No | 0.9037 ± 0.0193 | 0.8599 ± 0.0286 | 3761665 | GDNN | |
| []() | | No | 0.8781 ± 0.0474 | 0.8044 ± 0.0404 | 3761665 | GraphSAGE + Edge Attr | |
| Learning from Counterfactual Links for Link Prediction | ✓ Link | No | 0.8608 ± 0.0198 | 0.8405 ± 0.0284 | 837635 | CFLP (w/ JKNet) | 2021-06-03 |
| Distance-Enhanced Graph Neural Network for Link Prediction | ✓ Link | No | 0.8239 ± 0.0437 | 0.8206 ± 0.0298 | 3760134 | GraphSAGE+anchor distance | 2021-05-20 |
| Neural Common Neighbor with Completion for Link Prediction | ✓ Link | No | 0.8232 ± 0.0610 | 0.7172 ± 0.0025 | 1412098 | NeuralCommonNeighbor | 2023-02-02 |
| []() | | No | 0.7704 ± 0.0582 | 0.6928 ± 0.0096 | 2910817 | ELPH | |
| []() | | No | 0.7672 ± 0.0265 | 0.6713 ± 0.0071 | 1763329 | DEA + JKNet | |
| []() | | No | 0.7654 ± 0.0459 | 0.6927 ± 0.0054 | 2712931 | BUDDY | |
| Edge Proposal Sets for Link Prediction | ✓ Link | No | 0.7495 ± 0.0317 | 0.6696 ± 0.0198 | 1421057 | GraphSAGE+Edge Proposal Set | 2021-06-30 |
| []() | | No | 0.7385 ± 0.0871 | 0.7225 ± 0.0047 | 10235281 | LRGA+GCN(Node2Vec+Augment) | |
| Memory-Associated Differential Learning | ✓ Link | No | 0.6781 ± 0.0294 | 0.7010 ± 0.0082 | 1228897 | MAD Learning | 2021-02-10 |
| Global Attention Improves Graph Networks Generalization | ✓ Link | No | 0.6230 ± 0.0912 | 0.6675 ± 0.0058 | 1576081 | LRGA + GCN | 2020-06-14 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | No | 0.6056 ± 0.0869 | 0.6776 ± 0.0095 | 1421571 | GCN+JKNet | 2016-09-09 |
| Network In Graph Neural Network | | No | 0.5770 ± 0.1523 | 0.7323 ± 0.0040 | 1618433 | NGNN + GraphSAGE | 2021-11-23 |
| Network In Graph Neural Network | | No | 0.5483 ± 0.1581 | 0.7121 ± 0.0038 | 1487361 | NGNN + GCN | 2021-11-23 |
| Inductive Representation Learning on Large Graphs | ✓ Link | No | 0.5390 ± 0.0474 | 0.6262 ± 0.0037 | 1421057 | GraphSAGE | 2017-06-07 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | No | 0.3707 ± 0.0507 | 0.5550 ± 0.0208 | 1289985 | GCN | 2016-09-09 |
| Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning | ✓ Link | No | 0.3056 ± 0.0386 | 0.2849 ± 0.0269 | 531138 | SEAL | 2020-10-30 |
| node2vec: Scalable Feature Learning for Networks | ✓ Link | No | 0.2326 ± 0.0209 | 0.3292 ± 0.0121 | 645249 | Node2vec | 2016-07-03 |
| DeepWalk: Online Learning of Social Representations | ✓ Link | No | 0.2246 ± 0.0290 | Please tell us | 1543913 | DeepWalk | 2014-03-26 |
| []() | | No | 0.1861 ± 0.0000 | 0.0966 ± 0.0000 | 0 | Adamic Adar | |
| []() | | No | 0.1773 ± 0.0000 | 0.0947 ± 0.0000 | 0 | Common Neighbor | |
| Open Graph Benchmark: Datasets for Machine Learning on Graphs | ✓ Link | No | 0.1368 ± 0.0475 | 0.3370 ± 0.0264 | 1224193 | Matrix Factorization | 2020-05-02 |