| GNNDLD: Graph Neural Network with Directional Label Distribution | | 75.69±0.78 | GNNDLD | 2024-02-26 |
| Neighborhood Homophily-Guided Graph Convolutional Network | ✓ Link | 43.94 ± 1.14 | NHGCN | 2023-10-21 |
| Graph Neural Networks with Learnable and Optimal Polynomial Bases | ✓ Link | 43.05 ± 0.53 | FavardGNN | 2023-02-24 |
| Graph Neural Networks with Learnable and Optimal Polynomial Bases | ✓ Link | 42.39 ± 0.52 | OptBasisGNN | 2023-02-24 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.86 ± 1.48 | ACM-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.84 ± 1.15 | ACMII-GCN | 2022-10-14 |
| BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation | ✓ Link | 41.79 ± 1.01 | BernNet | 2021-06-21 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.79 ± 1.01 | ACM-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.66 ± 1.42 | ACMII-GCN++ | 2022-10-14 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 41.54 ± 0.99 | GCNII* | 2020-07-04 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.5 ± 1.54 | ACMII-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.4 ± 1.23 | ACM-Snowball-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.37 ± 1.37 | ACM-GCNII | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.27 ± 1.24 | ACM-GCNII* | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.27 ± 0.8 | ACM-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 41.1 ± 0.75 | ACMII-Snowball-2 | 2022-10-14 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 40.82 ± 1.79 | GCNII | 2020-07-04 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 40.31 ± 1.6 | ACMII-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 40.13 ± 1.21 | ACM-SGC-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 39.33 ± 1.25 | ACM-SGC-1 | 2022-10-14 |
| Adaptive Universal Generalized PageRank Graph Neural Network | ✓ Link | 39.30 ± 0.27 | GPRGNN | 2020-06-14 |
| Predict then Propagate: Graph Neural Networks meet Personalized PageRank | ✓ Link | 38.86 ± 0.24 | APPNP | 2018-10-14 |
| Beyond Low-frequency Information in Graph Convolutional Networks | ✓ Link | 38.85 ± 1.17 | H2GCN | 2021-01-04 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 38.58 ± 0.25 | MLP-2 | 2022-10-14 |
| Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity | ✓ Link | 36.84±0.62 | UGT | 2023-08-18 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 36.37 ± 0.21 | GraphSAGE | 2017-06-07 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 36.00 ± 1.36 | Snowball-3 | 2019-06-05 |
| Graph Attention Networks | ✓ Link | 35.98 ± 0.23 | GAT | 2017-10-30 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 35.97 ± 0.66 | Snowball-2 | 2019-06-05 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 35.51 ± 0.99 | GCN | 2016-09-09 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 35.41 ± 0.97 | GAT+JK | 2022-10-14 |
| MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | ✓ Link | 33.13 ± 2.40 | MixHop | 2019-04-30 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 32.72 ± 2.62 | GCN+JK | 2022-10-14 |
| Geom-GCN: Geometric Graph Convolutional Networks | ✓ Link | 31.63 | Geom-GCN* | 2020-02-13 |
| Beyond Low-frequency Information in Graph Convolutional Networks | ✓ Link | 31.59 ± 1.37 | FAGCN | 2021-01-04 |
| Simplifying Graph Convolutional Networks | ✓ Link | 28.81 ± 1.11 | SGC-2 | 2019-02-19 |
| Simplifying Graph Convolutional Networks | ✓ Link | 25.26 ± 1.18 | SGC-1 | 2019-02-19 |