| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 97.5 ± 1.25 | ACM-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 97.13 ± 1.68 | ACMII-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 97.00 ± 2.63 | ACMII-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 96.75 ± 1.79 | ACMII-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 96.63 ± 2.24 | ACMII-Snowball-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 96.62 ± 1.86 | ACM-Snowball-3 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 96.62 ± 2.44 | ACMII-GCN | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 96.5 ± 2.08 | ACM-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 96.38 ± 2.59 | ACM-Snowball-2 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 95.75 ± 2.03 | ACM-GCN | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 94.63 ± 2.96 | ACM-GCNII | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 94.37 ± 2.81 | ACM-GCNII* | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 94.00 ± 2.61 | ACM-SGC-2 | 2022-10-14 |
| New Benchmarks for Learning on Non-Homophilous Graphs | ✓ Link | 93.87 ± 3.33 | MLP-2 | 2021-04-03 |
| Adaptive Universal Generalized PageRank Graph Neural Network | ✓ Link | 93.75 ± 2.37 | GPRGNN | 2020-06-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 93.25 ± 2.92 | ACM-SGC-1 | 2022-10-14 |
| Predict then Propagate: Graph Neural Networks meet Personalized PageRank | ✓ Link | 92.00 ± 3.59 | APPNP | 2018-10-14 |
| Beyond Low-frequency Information in Graph Convolutional Networks | ✓ Link | 89.75 ± 6.37 | FAGCN | 2021-01-04 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 89.12 ± 3.06 | GCNII* | 2020-07-04 |
| Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs | ✓ Link | 87.5 ± 1.77 | H2GCN | 2020-06-20 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 83.25 ± 2.69 | GCNII | 2020-07-04 |
| MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | ✓ Link | 77.25 ± 7.80 | MixHop | 2019-04-30 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 75.5 ± 2.92 | GCN | 2016-09-09 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 74.88 ± 3.42 | Snowball-2 | 2019-06-05 |
| Simplifying Graph Convolutional Networks | ✓ Link | 74.75 ± 2.89 | SGC-2 | 2019-02-19 |
| Graph Attention Networks | ✓ Link | 71.01 ± 4.66 | GAT | 2017-10-30 |
| Simplifying Graph Convolutional Networks | ✓ Link | 70.38 ± 2.85 | SGC-1 | 2019-02-19 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 69.50 ± 3.12 | GAT+JK | 2022-10-14 |
| Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks | ✓ Link | 69.5 ± 5.01 | Snowball-3 | 2019-06-05 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 64.85 ± 5.14 | GraphSAGE | 2017-06-07 |
| Geom-GCN: Geometric Graph Convolutional Networks | ✓ Link | 64.12 | Geom-GCN* | 2020-02-13 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 62.50 ± 15.75 | GCN+JK | 2022-10-14 |