| GraphGPT: Graph Learning with Generative Pre-trained Transformers | ✓ Link | No | 0.9305 ± 0.0020 | 0.9295 ± 0.0022 | 133096832 | GraphGPT(d1n30) | 2023-12-31 |
| Pure Message Passing Can Estimate Common Neighbor for Link Prediction | ✓ Link | No | 0.9072 ± 0.0012 | 0.9074 ± 0.0011 | 749757283 | MPLP | 2023-09-02 |
| GraphGPT: Graph Learning with Generative Pre-trained Transformers | ✓ Link | No | 0.9055 ± 0.0016 | 0.9042 ± 0.0014 | 46784128 | GraphGPT(SMTP) | 2023-12-31 |
| Circle Feature Graphormer: Can Circle Features Stimulate Graph Transformer? | ✓ Link | No | 0.8997 ± 0.0015 | 0.8987 ± 0.0011 | 686253 | CFG | 2023-09-11 |
| []() | | No | 0.8957 ± 0.0010 | 0.8948 ± 0.0008 | 256802 | SIEG | |
| Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods | ✓ Link | No | 0.8891 ± 0.0005 | 0.8892 ± 0.0005 | 372674 | GCN + Heuristic Encoding | 2024-11-22 |
| Network In Graph Neural Network | | No | 0.8891 ± 0.0022 | 0.8879 ± 0.0022 | 1134402 | NGNN + SEAL | 2021-11-23 |
| Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning | ✓ Link | No | 0.8883 ± 0.0018 | 0.8891 ± 0.0021 | 79617 | SUREL | 2022-02-28 |
| Simplifying Subgraph Representation Learning for Scalable Link Prediction | ✓ Link | No | 0.8814 ± 0.0008 | 0.8809 ± 0.0074 | 142275001 | S3GRL (PoS Plus) | 2023-01-29 |
| []() | | No | 0.8796 ± 0.0008 | 0.8793 ± 0.0008 | 166531 | BUDDY | |
| Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning | ✓ Link | No | 0.8767 ± 0.0032 | 0.8757 ± 0.0031 | 260802 | SEAL | 2020-10-30 |
| Adaptive Graph Diffusion Networks | ✓ Link | No | 0.8549 ± 0.0029 | 0.8556 ± 0.0033 | 306716 | AGDN w/GraphSAINT | 2020-12-30 |
| Pairwise Learning for Neural Link Prediction | ✓ Link | No | 0.8492 ± 0.0029 | 0.8490 ± 0.0031 | 146514551 | PLNLP | 2021-12-06 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | No | 0.8474 ± 0.0021 | 0.8479 ± 0.0023 | 296449 | Full-batch GCN | 2016-09-09 |
| []() | | No | 0.8432 ± 0.0003 | 0.8422 ± 0.0002 | 749558528 | HPE - Pre-trained Initialized | |
| Inductive Representation Learning on Large Graphs | ✓ Link | No | 0.8260 ± 0.0036 | 0.8263 ± 0.0033 | 460289 | Full-batch GraphSAGE | 2017-06-07 |
| Inductive Representation Learning on Large Graphs | ✓ Link | No | 0.8044 ± 0.0010 | 0.8054 ± 0.0009 | 460289 | NeighborSampling (SAGE aggr) | 2017-06-07 |
| Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks | ✓ Link | No | 0.8004 ± 0.0025 | 0.7994 ± 0.0025 | 296449 | ClusterGCN (GCN aggr) | 2019-05-20 |
| GraphSAINT: Graph Sampling Based Inductive Learning Method | ✓ Link | No | 0.7985 ± 0.0040 | 0.7975 ± 0.0039 | 296449 | GraphSAINT (GCN aggr) | 2019-07-10 |
| node2vec: Scalable Feature Learning for Networks | ✓ Link | No | 0.6141 ± 0.0011 | 0.6124 ± 0.0011 | 374911105 | Node2vec | 2016-07-03 |
| []() | | No | 0.5189 ± 0.0000 | 0.5167 ± 0.0000 | 0 | Adamic Adar | |
| Open Graph Benchmark: Datasets for Machine Learning on Graphs | ✓ Link | No | 0.5186 ± 0.0443 | 0.5181 ± 0.0436 | 281113505 | Matrix Factorization | 2020-05-02 |
| []() | | No | 0.5147 ± 0.0000 | 0.5119 ± 0.0000 | 0 | Common Neighbor | |