| []() | | 0.8789 ± 0.0024 | No | 0.8836 ± 0.0028 | 7720368 | LDHGNN | |
| Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks | ✓ Link | 0.7956 ± 0.0047 | No | 0.8021 ± 0.0020 | 7720368 | CLGNN | 2024-02-29 |
| []() | | 0.5794 ± 0.0018 | No | 0.5997 ± 0.0012 | 8469021 | HGAMLP+LP+MS(LINE embs) | |
| Long-range Meta-path Search on Large-scale Heterogeneous Graphs | ✓ Link | 0.5784 ± 0.0022 | No | 0.5951 ± 0.0007 | 16470044 | LMSPS (w/o embs) | 2023-07-17 |
| Efficient Heterogeneous Graph Learning via Random Projection | ✓ Link | 0.5773 ± 0.0012 | No | 0.5973 ± 0.0008 | 7720368 | RpHGNN+LP+CR (LINE embs) | 2023-10-23 |
| Long-range Meta-path Search on Large-scale Heterogeneous Graphs | ✓ Link | 0.5767 ± 0.0015 | No | 0.5902 ± 0.0016 | 16470044 | LMSPS(w/o ComplEx embs) | 2023-07-17 |
| Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials | ✓ Link | 0.5752 ± 0.0011 | No | 0.5943 ± 0.0015 | 4852434 | PSHGCN (ComplEx embs) | 2023-05-31 |
| Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials | ✓ Link | 0.5752 ± 0.0011 | No | 0.5943 ± 0.0015 | 4852434 | PSHGCN | 2023-05-31 |
| Long-range Meta-path Search on Large-scale Heterogeneous Graphs | ✓ Link | 0.5739 ± 0.0012 | No | 0.5888 ± 0.0015 | 13177884 | LDMLP(w/o ComplEx embs) | 2023-07-17 |
| Simple and Efficient Heterogeneous Graph Neural Network | ✓ Link | 0.5719 ± 0.0012 | No | 0.5917 ± 0.0009 | 8371231 | SeHGNN (ComplEx embs) | 2022-07-06 |
| Simple and Efficient Heterogeneous Graph Neural Network | ✓ Link | 0.5671 ± 0.0014 | No | 0.5870 ± 0.0008 | 8371231 | SeHGNN | 2022-07-06 |
| SCR: Training Graph Neural Networks with Consistency Regularization | ✓ Link | 0.5631 ± 0.0021 | No | 0.5734 ± 0.0035 | 6734882 | NARS-GAMLP+RLU+SCR | 2021-12-08 |
| Graph Attention Multi-Layer Perceptron | ✓ Link | 0.5590 ± 0.0027 | No | 0.5702 ± 0.0041 | 6734882 | NARS-GAMLP+RLU | 2022-06-09 |
| []() | | 0.5590 ± 0.0027 | No | 0.5702 ± 0.0041 | 6734882 | NARS-GAMLP+RLU | |
| SCR: Training Graph Neural Networks with Consistency Regularization | ✓ Link | 0.5451 ± 0.0019 | No | 0.5590 ± 0.0028 | 6734882 | NARS-GAMLP+SCR-m | 2021-12-08 |
| Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training | ✓ Link | 0.5440 ± 0.0015 | No | 0.5591 ± 0.0017 | 3846330 | NARS_SAGN+SLE | 2021-04-19 |
| SCR: Training Graph Neural Networks with Consistency Regularization | ✓ Link | 0.5432 ± 0.0018 | No | 0.5654 ± 0.0021 | 6734882 | NARS-GAMLP+SCR | 2021-12-08 |
| Graph Attention Multi-Layer Perceptron | ✓ Link | 0.5396 ± 0.0018 | No | 0.5548 ± 0.0008 | 6734882 | NARS-GAMLP | 2022-06-09 |
| []() | | 0.5396 ± 0.0018 | No | 0.5548 ± 0.0008 | 6734882 | NARS-GAMLP | |
| Label-Enhanced Graph Neural Network for Semi-supervised Node Classification | ✓ Link | 0.5378 ± 0.0016 | No | 0.5528 ± 0.0013 | 5147997 | LEGNN + AS-Train | 2022-05-31 |
| Label-Enhanced Graph Neural Network for Semi-supervised Node Classification | ✓ Link | 0.5276 ± 0.0014 | No | 0.5443 ± 0.0009 | 5147997 | LEGNN | 2022-05-31 |
| Scalable Graph Neural Networks for Heterogeneous Graphs | ✓ Link | 0.5240 ± 0.0016 | No | 0.5372 ± 0.0009 | 4130149 | NARS | 2020-11-19 |
| Heterogeneous Graph Representation Learning with Relation Awareness | ✓ Link | 0.5204 ± 0.0026 | No | 0.5361 ± 0.0022 | 5638053 | R-HGNN | 2021-05-24 |
| Residual Network and Embedding Usage: New Tricks of Node Classification with Graph Convolutional Networks | ✓ Link | 0.5109 ± 0.0038 | No | 0.5295 ± 0.0042 | 309777252 | R-GSN + metapath2vec | 2021-05-18 |
| Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning | ✓ Link | 0.5045 ± 0.0017 | No | 0.5300 ± 0.0018 | 2850405 | HGConv | 2020-12-29 |
| Modeling Relational Data with Graph Convolutional Networks | ✓ Link | 0.5032 ± 0.0037 | No | 0.5182 ± 0.0041 | 154373028 | R-GSN | 2017-03-17 |
| Heterogeneous Graph Transformer | ✓ Link | 0.4982 ± 0.0013 | No | 0.5124 ± 0.0046 | 26877657 | HGT (TransE embs) | 2020-03-03 |
| GraphSAINT: Graph Sampling Based Inductive Learning Method | ✓ Link | 0.4966 ± 0.0022 | No | 0.5066 ± 0.0017 | 309764724 | GraphSAINT + metapath2vec | 2019-07-10 |
| Heterogeneous Graph Transformer | ✓ Link | 0.4927 ± 0.0061 | No | 0.4989 ± 0.0047 | 21173389 | HGT (LADIES Sample) | 2020-03-03 |
| GraphSAINT: Graph Sampling Based Inductive Learning Method | ✓ Link | 0.4751 ± 0.0022 | No | 0.4837 ± 0.0026 | 154366772 | GraphSAINT (R-GCN aggr) | 2019-07-10 |
| Robust Optimization as Data Augmentation for Large-scale Graphs | ✓ Link | 0.4737 ± 0.0048 | No | 0.4835 ± 0.0036 | 154366772 | R-GCN+FLAG | 2020-10-19 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 0.4678 ± 0.0067 | No | 0.4761 ± 0.0068 | 154366772 | NeighborSampling (R-GCN aggr) | 2017-06-07 |
| SIGN: Scalable Inception Graph Neural Networks | ✓ Link | 0.4046 ± 0.0012 | No | 0.4068 ± 0.0010 | 3724645 | SIGN | 2020-04-23 |
| Modeling Relational Data with Graph Convolutional Networks | ✓ Link | 0.3977 ± 0.0046 | No | 0.4084 ± 0.0041 | 154366772 | Full-batch R-GCN | 2017-03-17 |
| Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks | ✓ Link | 0.3732 ± 0.0037 | No | 0.3840 ± 0.0031 | 154366772 | ClusterGCN (R-GCN aggr) | 2019-05-20 |
| metapath2vec: Scalable Representation Learning for Heterogeneous Networks | ✓ Link | 0.3544 ± 0.0036 | No | 0.3506 ± 0.0017 | 94479069 | MetaPath2vec | 2017-08-01 |
| []() | | 0.3544 ± 0.0036 | No | 0.3506 ± 0.0017 | 94479069 | MetaPath2vec | |
| Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 0.2761 ± 0.0018 | No | 0.2646 ± 0.0013 | 278202 | CoLinkDistMLP | 2021-06-16 |
| Open Graph Benchmark: Datasets for Machine Learning on Graphs | ✓ Link | 0.2692 ± 0.0026 | No | 0.2626 ± 0.0016 | 188509 | MLP | 2020-05-02 |