| Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias | ✓ Link | Yes | 0.8942 ± 0.0007 | 0.9527 ± 0.0007 | 664233700 | LD+GAT | 2023-09-26 |
| GIPA: A General Information Propagation Algorithm for Graph Learning | ✓ Link | No | 0.8917 ± 0.0007 | 0.9472 ± 0.0020 | 17438716 | GIPA(Wide&Deep) | 2023-01-19 |
| Adaptive Graph Diffusion Networks | ✓ Link | No | 0.8865 ± 0.0013 | 0.9418 ± 0.0005 | 8605486 | AGDN | 2020-12-30 |
| Training Graph Neural Networks with 1000 Layers | ✓ Link | No | 0.8824 ± 0.0015 | 0.9450 ± 0.0008 | 68471608 | RevGNN-Wide | 2021-06-14 |
| Network In Graph Neural Network | | No | 0.8809 ± 0.0016 | 0.9375 ± 0.0019 | 11740552 | GAT+BOT+NGNN | 2021-11-23 |
| Training Graph Neural Networks with 1000 Layers | ✓ Link | No | 0.8774 ± 0.0013 | 0.9326 ± 0.0006 | 20031384 | RevGNN-Deep | 2021-06-14 |
| Bag of Tricks for Node Classification with Graph Neural Networks | ✓ Link | No | 0.8765 ± 0.0008 | 0.9280 ± 0.0008 | 2484192 | GAT+BoT | 2021-03-24 |
| Graph Attention Networks | ✓ Link | No | 0.8711 ± 0.0007 | 0.9217 ± 0.0011 | 6360470 | GAT + labels + node2vec | 2017-10-30 |
| GIPA: General Information Propagation Algorithm for Graph Learning | ✓ Link | No | 0.8700 ± 0.0010 | 0.9187 ± 0.0003 | 4831056 | GIPA | 2021-05-13 |
| Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification | ✓ Link | No | 0.8691 ± 0.0018 | 0.9258 ± 0.0009 | 1959984 | UniMP+CrossEdgeFeat | 2020-09-08 |
| Bag of Tricks for Node Classification with Graph Neural Networks | ✓ Link | No | 0.8682 ± 0.0021 | 0.9194 ± 0.0003 | 2475232 | GAT+EdgeFeatureAtt | 2021-03-24 |
| Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification | ✓ Link | No | 0.8642 ± 0.0008 | 0.9175 ± 0.0006 | 1909104 | UniMP | 2020-09-08 |
| Robust Optimization as Data Augmentation for Large-scale Graphs | ✓ Link | No | 0.8596 ± 0.0027 | 0.9132 ± 0.0022 | 2374568 | DeeperGCN+FLAG | 2020-10-19 |
| DeeperGCN: All You Need to Train Deeper GCNs | ✓ Link | No | 0.8580 ± 0.0017 | 0.9106 ± 0.0016 | 2374568 | DeeperGCN | 2020-06-13 |
| Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification | ✓ Link | No | 0.8501 ± 0.0046 | 0.9067 ± 0.0043 | 2943472 | GAT | 2024-06-13 |
| []() | | No | 0.8496 ± 0.0028 | 0.8971 ± 0.0011 | 2374456 | DeepGCN | |
| []() | | No | 0.8436 ± 0.0065 | 0.8973 ± 0.0057 | 538544 | MWE-DGCN | |
| DeeperGCN: All You Need to Train Deeper GCNs | ✓ Link | No | 0.8251 ± 0.0043 | 0.8656 ± 0.0037 | 487436 | GEN + FLAG + node2vec | 2020-06-13 |
| Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification | ✓ Link | No | 0.8221 ± 0.0032 | 0.8831 ± 0.0044 | 2444896 | GraphSAGE | 2024-06-13 |
| []() | | No | 0.7916 ± 0.0086 | 0.8256 ± 0.0057 | 90608 | DVCNN | |
| Bandit Samplers for Training Graph Neural Networks | ✓ Link | No | 0.7825 ± 0.0035 | Please tell us | 316754 | GeniePath-BS | 2020-06-10 |
| GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs | ✓ Link | No | 0.7803 ± 0.0073 | Please tell us | Please tell us | GaAN | 2018-03-20 |
| Inductive Representation Learning on Large Graphs | ✓ Link | No | 0.7768 ± 0.0020 | 0.8334 ± 0.0013 | 193136 | GraphSAGE | 2017-06-07 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | No | 0.7251 ± 0.0035 | 0.7921 ± 0.0018 | 96880 | GCN | 2016-09-09 |
| Open Graph Benchmark: Datasets for Machine Learning on Graphs | ✓ Link | No | 0.7204 ± 0.0048 | 0.7706 ± 0.0014 | 96880 | MLP | 2020-05-02 |
| node2vec: Scalable Feature Learning for Networks | ✓ Link | No | 0.6881 ± 0.0065 | 0.7007 ± 0.0053 | 17094000 | Node2vec | 2016-07-03 |