| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 67.5±0.53 | ACMII-GCN+++ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 67.44±0.31 | ACMII-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 67.4±0.44 | ACM-GCN+ | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 67.3±0.48 | ACM-GCN++ | 2022-10-14 |
| Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs | ✓ Link | 67.22±0.90 | H2GCN | 2020-06-20 |
| Predict then Propagate: Graph Neural Networks meet Personalized PageRank | ✓ Link | 67.21±0.56 | APPNP | 2018-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 67.15±0.41 | ACMII-GCN | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 67.01±0.38 | ACM-GCN | 2022-10-14 |
| Adaptive Universal Generalized PageRank Graph Neural Network | ✓ Link | 66.90±0.50 | GPRGNN | 2020-06-14 |
| Beyond Low-frequency Information in Graph Convolutional Networks | ✓ Link | 66.86±0.53 | FAGCN | 2021-01-04 |
| MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing | ✓ Link | 66.80±0.58 | MixHop | 2019-04-30 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 66.67±0.56 | ACM-SGC-1 | 2022-10-14 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 66.6±0.57 | ACM-GCNII* | 2022-10-14 |
| New Benchmarks for Learning on Non-Homophilous Graphs | ✓ Link | 66.55±0.72 | MLP-2 | 2021-04-03 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 66.53±0.57 | ACM-SGC-2 | 2022-10-14 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 66.42±0.56 | GCNII* | 2020-07-04 |
| Revisiting Heterophily For Graph Neural Networks | ✓ Link | 66.39±0.56 | ACM-GCNII | 2022-10-14 |
| Simple and Deep Graph Convolutional Networks | ✓ Link | 66.38±0.45 | GCNII | 2020-07-04 |
| Combining Label Propagation and Simple Models Out-performs Graph Neural Networks | ✓ Link | 64.60±0.57 | C&S(1hop) | 2020-10-27 |
| Combining Label Propagation and Simple Models Out-performs Graph Neural Networks | ✓ Link | 64.52±0.62 | C&S(2hop) | 2020-10-27 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 62.23±0.53 | GCN | 2016-09-09 |
| Graph Attention Networks | ✓ Link | 61.09±0.77 | GAT | 2017-10-30 |
| New Benchmarks for Learning on Non-Homophilous Graphs | ✓ Link | 60.99±0.14 | GCN+JK | 2021-04-03 |
| Simplifying Graph Convolutional Networks | ✓ Link | 59.73±0.12 | SGC-1 | 2019-02-19 |
| New Benchmarks for Learning on Non-Homophilous Graphs | ✓ Link | 59.66±0.92 | GAT+JK | 2021-04-03 |
| New Benchmarks for Learning on Non-Homophilous Graphs | ✓ Link | 57.71±0.36 | LINK | 2021-04-03 |
| New Benchmarks for Learning on Non-Homophilous Graphs | ✓ Link | 56.96±0.26 | LProp (2hop) | 2021-04-03 |
| New Benchmarks for Learning on Non-Homophilous Graphs | ✓ Link | 56.50±0.41 | L Prop (1hop) | 2021-04-03 |