| Edge2Node: Reducing Edge Prediction to Node Classification | | No | 0.8911 ± 0.1266 | 0.8857 ± 0.1331 | 526851 | ** E2N** | 2023-11-06 |
| Reconsidering the Performance of GAE in Link Prediction | ✓ Link | No | 0.7334 ± 0.0092 | 0.7391 ± 0.0178 | 295848449 | Refined-GAE | 2024-11-06 |
| GraphGPT: Graph Learning with Generative Pre-trained Transformers | ✓ Link | No | 0.6876 ± 0.0067 | 0.7017 ± 0.0044 | 145263360 | GraphGPT(SMTP) | 2023-12-31 |
| Pure Message Passing Can Estimate Common Neighbor for Link Prediction | ✓ Link | No | 0.6524 ± 0.0150 | 0.6685 ± 0.0073 | 147794531 | MPLP | 2023-09-02 |
| Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods | ✓ Link | No | 0.6354 ± 0.0121 | 0.6524 ± 0.0096 | 148144898 | GCN (node embedding) | 2024-11-22 |
| []() | | No | 0.6322 ± 0.0174 | 0.6533 ± 0.0234 | 1993965 | SIEG | |
| Neural Common Neighbor with Completion for Link Prediction | ✓ Link | No | 0.6119 ± 0.0085 | 0.6021 ± 0.0037 | 33538 | **Neural Common Neighbor ** | 2023-02-02 |
| Network In Graph Neural Network | | No | 0.5971 ± 0.0245 | 0.5995 ± 0.0205 | 735426 | NGNN + SEAL | 2021-11-23 |
| []() | | No | 0.5432 ± 0.0044 | 0.5492 ± 0.0112 | 52802 | SUREL+ | |
| SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning | ✓ Link | No | 0.5432 ± 0.0044 | 0.5492 ± 0.0112 | 52802 | SUREL+ | 2023-03-06 |
| Edge Proposal Sets for Link Prediction | ✓ Link | No | 0.5324 ± 0.0000 | 0.5142 ± 0.0000 | 0 | RA+Edge Proposal Set | 2021-06-30 |
| []() | | No | 0.5062 ± 0.0035 | 0.4906 ± 0.0029 | 163330 | MLP+CN&RA&AA | |
| []() | | No | 0.4934 ± 0.0098 | 0.4931 ± 0.0025 | 644 | BUDDY | |
| Predicting Missing Links via Local Information | ✓ Link | No | 0.4933 ± 0.0000 | 0.4722 ± 0.0000 | 0 | Resource Allocation | 2009-01-05 |
| Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning | ✓ Link | No | 0.4880 ± 0.0316 | 0.5125 ± 0.0252 | 709122 | SEAL | 2020-10-30 |
| Simplifying Subgraph Representation Learning for Scalable Link Prediction | ✓ Link | No | 0.4242 ± 0.0180 | 0.6512 ± 0.0109 | 32270001 | S3GRL (PoS Plus) | 2023-01-29 |
| Adaptive Graph Diffusion Networks | ✓ Link | No | 0.4123 ± 0.0159 | 0.4332 ± 0.0092 | 36904259 | AGDN | 2020-12-30 |
| Network In Graph Neural Network | | No | 0.4005 ± 0.0138 | 0.4058 ± 0.0123 | 556033 | NGNN + GraphSAGE | 2021-11-23 |
| Network In Graph Neural Network | | No | 0.3683 ± 0.0099 | 0.3834 ± 0.0082 | 410113 | NGNN + GCN | 2021-11-23 |
| []() | | No | 0.3245 ± 0.0000 | 0.3268 ± 0.0000 | 0 | Adamic Adar | |
| Open Graph Benchmark: Datasets for Machine Learning on Graphs | ✓ Link | No | 0.3229 ± 0.0094 | 0.3228 ± 0.0428 | 147662849 | Matrix Factorization | 2020-05-02 |
| []() | | No | 0.2765 ± 0.0000 | 0.2823 ± 0.0000 | 0 | Common Neighbor | |
| DeepWalk: Online Learning of Social Representations | ✓ Link | No | 0.2302 ± 0.0163 | Please tell us | 150138741 | DeepWalk | 2014-03-26 |
| node2vec: Scalable Feature Learning for Networks | ✓ Link | No | 0.2226 ± 0.0083 | 0.2253 ± 0.0088 | 73878913 | Node2vec | 2016-07-03 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | No | 0.1867 ± 0.0132 | 0.1845 ± 0.0140 | 278529 | GCN | 2016-09-09 |
| Inductive Representation Learning on Large Graphs | ✓ Link | No | 0.1655 ± 0.0240 | 0.1724 ± 0.0264 | 424449 | GraphSAGE | 2017-06-07 |