Node Classification On Non Homophilic 11
평가 지표
1:1 Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | 1:1 Accuracy |
|---|---|
| beyond-low-frequency-information-in-graph | 46.07 ± 2.11 |
| non-local-graph-neural-networks | 50.7 ± 2.2 |
| revisiting-heterophily-for-graph-neural | 74.47 ± 1.84 |
| revisiting-heterophily-for-graph-neural | 69.14 ± 1.91 |
| neural-sheaf-diffusion-a-topological | 68.68 ± 1.73 |
| neural-sheaf-diffusion-a-topological | 68.04 ± 1.58 |
| revisiting-heterophily-for-graph-neural | 68.46 ± 1.7 |
| edge-directionality-improves-learning-on | 79.71±1.26 |
| revisiting-heterophily-for-graph-neural | 74.41 ± 1.49 |
| joint-adaptive-feature-smoothing-and-topology | 62.59 ± 2.04 |
| scale-invariance-of-graph-neural-networks | 80.1±1.5 |
| neural-sheaf-diffusion-a-topological | 67.93 ± 1.58 |
| revisiting-heterophily-for-graph-neural | 74.76 ± 2.2 |
| revisiting-heterophily-for-graph-neural | 74.56 ± 2.08 |
| non-local-graph-neural-networks | 65.7 ± 1.4 |
| breaking-the-limit-of-graph-neural-networks | 65.24 ± 0.87 |
| addressing-heterophily-in-node-classification | 77.05 ± 1.24 |
| mixhop-higher-order-graph-convolution | 60.50 ± 2.53 |
| finding-global-homophily-in-graph-neural | 71.21 ± 1.84 |
| generalizing-graph-neural-networks-beyond | 60.11 ± 2.15 |
| geom-gcn-geometric-graph-convolutional-1 | 60.00 ± 2.81 |
| finding-global-homophily-in-graph-neural | 69.78 ± 2.42 |
| deformable-graph-convolutional-networks | 70.90 ±1.12 |
| non-local-graph-neural-networks | 70.1 ± 2.9 |
| simple-and-deep-graph-convolutional-networks-1 | 63.86 ± 3.04 |
| large-scale-learning-on-non-homophilous | 68.42 ± 1.38 |
| two-sides-of-the-same-coin-heterophily-and | 71.14 ±1.84 |
| revisiting-heterophily-for-graph-neural | 59.21 ± 2.22 |
| revisiting-heterophily-for-graph-neural | 63.99 ± 1.66 |