| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 96.56 ± 2 | ACM-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 95.74 ± 2.22 | ACM-Snowball-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 95.41 ± 2.82 | 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 ± 2.07 | ACMII-GCN | 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 ± 2.41 | ACM-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 94.75 ± 3.09 | ACMII-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 94.75 ± 2.91 | ACMII-GCN++ | 2022-10-14 |
| Node-oriented Spectral Filtering for Graph Neural Networks | ✓ Link | 94.03±0.82 | NFGNN | 2022-12-07 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.61 ± 1.55 | ACM-SGC-1 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.44 ± 2.54 | ACM-SGC-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.28 ± 2.79 | ACM-GCNII* | 2022-10-14 |
| BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation | ✓ Link | 93.12 ± 0.65 | BernNet | 2021-06-21 |
| Adaptive Universal Generalized PageRank Graph Neural Network | ✓ Link | 92.92 ± 0.61 | GPRGNN | 2020-06-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 92.46 ± 1.97 | ACM-GCNII | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 92.26 ± 0.71 | MLP-2 | 2022-10-14 |
| Predict then Propagate: Graph Neural Networks meet Personalized PageRank | ✓ Link | 91.18 ± 0.70 | APPNP | 2018-10-14 |
| Beyond Low-frequency Information in Graph Convolutional Networks | ✓ Link | 88.85 ± 4.39 | FAGCN | 2021-01-04 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 88.52 ± 3.02 | GCNII* | 2020-07-04 |
| Half-Hop: A graph upsampling approach for slowing down message passing | ✓ Link | 85.95 ± 6.42 | HH-GraphSAGE | 2023-08-17 |
| Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs | ✓ Link | 85.90 ± 3.53 | H2GCN | 2020-06-20 |
| Simplifying Graph Convolutional Networks | ✓ Link | 83.28 ± 5.43 | SGC-1 | 2019-02-19 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 83.11 ± 3.2 | GCN | 2016-09-09 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 83.11 ± 3.2 | Snowball-2 | 2019-06-05 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 83.11 ± 3.2 | Snowball-3 | 2019-06-05 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 82.46 ± 4.58 | GCNII | 2020-07-04 |
| Simplifying Graph Convolutional Networks | ✓ Link | 81.31 ± 3.3 | SGC-2 | 2019-02-19 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 80.66 ± 1.91 | GCN+JK | 2022-10-14 |
| Half-Hop: A graph upsampling approach for slowing down message passing | ✓ Link | 80.54 ± 4.80 | HH-GAT | 2023-08-17 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 79.03 ± 1.20 | GraphSAGE | 2017-06-07 |
| Graph Attention Networks | ✓ Link | 78.87 ± 0.86 | GAT | 2017-10-30 |
| MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | ✓ Link | 76.39 ± 7.66 | MixHop | 2019-04-30 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 75.41 ± 7.18 | GAT+JK | 2022-10-14 |
| Half-Hop: A graph upsampling approach for slowing down message passing | ✓ Link | 71.89 ± 3.46 | HH-GCN | 2023-08-17 |
| Geom-GCN: Geometric Graph Convolutional Networks | ✓ Link | 67.57 | Geom-GCN* | 2020-02-13 |