| Clenshaw Graph Neural Networks | ✓ Link | 91.69 ± 0.25 | ClenshawGCN | 2022-10-29 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 91.44 ± 0.08 | ACM-GCN | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 91.4 ± 0.07 | ACM-GCN++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 91.33 ± 0.11 | ACM-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 91.19 ± 0.16 | ACMII-GCN | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 91.13 ± 0.09 | ACMII-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 91.01 ± 0.18 | ACMII-GCN++ | 2022-10-14 |
| Finding Global Homophily in Graph Neural Networks When Meeting Heterophily | ✓ Link | 90.91 ± 0.13 | GloGNN++ | 2022-05-15 |
| Graph Neural Networks with Learnable and Optimal Polynomial Bases | ✓ Link | 90.83±0.11 | OptBasisGNN | 2023-02-24 |
| Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods | ✓ Link | 90.77 ± 0.27 | LINKX | 2021-10-27 |
| Finding Global Homophily in Graph Neural Networks When Meeting Heterophily | ✓ Link | 90.66 ± 0.11 | GloGNN | 2022-05-15 |
| MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | ✓ Link | 90.58 ± 0.16 | MixHop | 2019-04-30 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 90.24 ± 0.09 | GCNII | 2020-07-04 |
| Adaptive Universal Generalized PageRank Graph Neural Network | ✓ Link | 90.05 ± 0.31 | GPRGCN | 2020-06-14 |
| Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods | ✓ Link | 89.30 ± 0.19 | GCNJK | 2021-10-27 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 87.42 ± 0.37 | GCN | 2016-09-09 |
| Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods | ✓ Link | 86.68 ± 0.09 | MLP | 2021-10-27 |
| Predict then Propagate: Graph Neural Networks meet Personalized PageRank | ✓ Link | 85.36 ± 0.62 | APPNP | 2018-10-14 |
| Combining Label Propagation and Simple Models Out-performs Graph Neural Networks | ✓ Link | 84.94 ± 0.49 | C&S 2-hop | 2020-10-27 |
| Combining Label Propagation and Simple Models Out-performs Graph Neural Networks | ✓ Link | 82.93 ± 0.15 | C&S 1-hop | 2020-10-27 |
| Simplifying Graph Convolutional Networks | ✓ Link | 82.36 ± 0.37 | SGC 1-hop | 2019-02-19 |
| Simplifying Graph Convolutional Networks | ✓ Link | 82.10 ± 0.14 | SGC 2-hop | 2019-02-19 |
| Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods | ✓ Link | 73.56 ± 0.14 | LINK | 2021-10-27 |
| Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods | ✓ Link | 67.04 ± 0.20 | L Prop 2-hop | 2021-10-27 |
| Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods | ✓ Link | 66.02 ± 0.16 | L Prop 1-hop | 2021-10-27 |
| Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods | ✓ Link | 56.70 ± 2.07 | GATJK | 2021-10-27 |