| GNNDLD: Graph Neural Network with Directional Label Distribution | | 92.99 ±0.9 | GNNDLD | 2024-02-26 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.75 ± 1.16 | ACM-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.59 ± 1.58 | ACM-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.52 ± 0.43 | GAT+JK | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.47 ± 1.08 | ACMII-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.36 ± 1.26 | ACMII-Snowball-3 | 2022-10-14 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 89.33 ± 1.3 | Snowball-3 | 2019-06-05 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.33 ± 0.81 | ACM-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.18 ± 1.11 | ACMII-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.1 ± 1.61 | ACM-GCNII | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.00 ± 1.35 | ACM-GCNII* | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 89.00 ± 0.72 | ACMII-GCN | 2022-10-14 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 88.98 ± 1.33 | GCNII | 2020-07-04 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 88.95 ± 1.04 | ACMII-Snowball-2 | 2022-10-14 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 88.93 ± 1.37 | GCNII* | 2020-07-04 |
| Beyond Low-frequency Information in Graph Convolutional Networks | ✓ Link | 88.85 ± 1.36 | FAGCN | 2021-01-04 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 88.83 ± 1.49 | ACM-Snowball-2 | 2022-10-14 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 88.64 ± 1.15 | Snowball-2 | 2019-06-05 |
| BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation | ✓ Link | 88.52 ± 0.95 | BernNet | 2021-06-21 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 87.78 ± 0.96 | GCN | 2016-09-09 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 87.64 ± 0.99 | ACM-SGC-2 | 2022-10-14 |
| Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs | ✓ Link | 87.52 ± 0.61 | H2GCN | 2020-06-20 |
| 007: Democratically Finding The Cause of Packet Drops | ✓ Link | 86.90 ± 1.51 | GCN+JK | 2018-02-20 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 86.63 ± 1.13 | ACM-SGC-1 | 2022-10-14 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 86.58 ± 0.26 | GraphSAGE | 2017-06-07 |
| Simplifying Graph Convolutional Networks | ✓ Link | 85.48 ± 1.48 | SGC-2 | 2019-02-19 |
| Geom-GCN: Geometric Graph Convolutional Networks | ✓ Link | 85.27 | Geom-GCN* | 2020-02-13 |
| Simplifying Graph Convolutional Networks | ✓ Link | 85.12 ± 1.64 | SGC-1 | 2019-02-19 |
| Adaptive Universal Generalized PageRank Graph Neural Network | ✓ Link | 79.51 ± 0.36 | GPRGNN | 2020-06-14 |
| Predict then Propagate: Graph Neural Networks meet Personalized PageRank | ✓ Link | 79.41 ± 0.38 | APPNP | 2018-10-14 |
| Graph Attention Networks | ✓ Link | 76.70 ± 0.42 | GAT | 2017-10-30 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 76.44 ± 0.30 | MLP-2 | 2022-10-14 |
| MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | ✓ Link | 65.65 ± 11.31 | MixHop | 2019-04-30 |