| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 95.9 ± 1.83 | ACMII-GCN | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 95.25 ± 1.55 | ACMII-Snowball-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 95.08 ± 3.11 | ACM-Snowball-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 94.92 ± 2.79 | ACM-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 94.75 ± 3.8 | ACM-GCN | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 94.26 ± 2.57 | ACM-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.93 ± 1.05 | ACM-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.93 ± 3.03 | ACMII-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.77 ± 2.17 | ACM-SGC-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.77 ± 1.91 | ACM-SGC-1 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.61 ± 2.79 | ACMII-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.44 ± 2.74 | ACM-GCNII* | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 92.62 ± 2.57 | ACMII-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 92.62 ± 3.13 | ACM-GCNII | 2022-10-14 |
| BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation | ✓ Link | 92.13 ± 1.64 | BernNet | 2021-06-21 |
| Predict then Propagate: Graph Neural Networks meet Personalized PageRank | ✓ Link | 91.80 ± 0.63 | APPNP | 2018-10-14 |
| Adaptive Universal Generalized PageRank Graph Neural Network | ✓ Link | 91.36 ± 0.70 | GPRGNN | 2020-06-14 |
| Adaptive Universal Generalized PageRank Graph Neural Network | ✓ Link | 91.30 ± 0.70 | MLP-2 | 2020-06-14 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 90.49 ± 4.45 | GCNII* | 2020-07-04 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 89.18 ± 3.96 | GCNII | 2020-07-04 |
| Beyond Low-frequency Information in Graph Convolutional Networks | ✓ Link | 88.03 ± 5.6 | FAGCN | 2021-01-04 |
| Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs | ✓ Link | 86.23 ± 4.71 | H2GCN | 2020-06-20 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 82.95 ± 2.1 | Snowball-3 | 2019-06-05 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 82.62 ± 2.34 | Snowball-2 | 2019-06-05 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 82.46 ± 3.11 | GCN | 2016-09-09 |
| Graph Attention Networks | ✓ Link | 76.00 ± 1.01 | GAT | 2017-10-30 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 74.43 ± 10.24 | GAT+JK | 2022-10-14 |
| Simplifying Graph Convolutional Networks | ✓ Link | 72.62 ± 9.92 | SGC-2 | 2019-02-19 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 71.41 ± 1.24 | GraphSAGE | 2017-06-07 |
| Simplifying Graph Convolutional Networks | ✓ Link | 70.98 ± 8.39 | SGC-1 | 2019-02-19 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 66.56 ± 13.82 | GCN+JK | 2022-10-14 |
| Geom-GCN: Geometric Graph Convolutional Networks | ✓ Link | 60.81 | Geom-GCN* | 2020-02-13 |
| MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | ✓ Link | 60.33 ± 28.53 | MixHop | 2019-04-30 |