Node Classification On Non Homophilic 10
평가 지표
1:1 Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | 1:1 Accuracy |
|---|---|
| non-local-graph-neural-networks | 29.5 ± 1.3 |
| revisiting-heterophily-for-graph-neural | 35.49 ± 1.06 |
| mixhop-higher-order-graph-convolution | 32.22 ± 2.34 |
| revisiting-heterophily-for-graph-neural | 37.31 ± 1.09 |
| revisiting-heterophily-for-graph-neural | 36.63 ± 0.84 |
| revisiting-heterophily-for-graph-neural | 36.31 ± 1.2 |
| non-local-graph-neural-networks | 37.9 ± 1.3 |
| generalizing-graph-neural-networks-beyond | 35.70 ± 1.00 |
| neural-sheaf-diffusion-a-topological | 37.79 ± 1.01 |
| two-sides-of-the-same-coin-heterophily-and | 37.54 ± 1.56 |
| geom-gcn-geometric-graph-convolutional-1 | 31.59 ± 1.15 |
| revisiting-heterophily-for-graph-neural | 36.14 ± 1.44 |
| two-sides-of-the-same-coin-heterophily-and | 35.16 ± 0.9 |
| finding-global-homophily-in-graph-neural | 37.35 ± 1.30 |
| neural-sheaf-diffusion-a-topological | 37.80 ± 1.22 |
| deformable-graph-convolutional-networks | 37.07±0.79 |
| simple-and-deep-graph-convolutional-networks-1 | 37.44 ± 1.30 |
| finding-global-homophily-in-graph-neural | 37.70 ± 1.40 |
| large-scale-learning-on-non-homophilous | 36.10 ± 1.55 |
| revisiting-heterophily-for-graph-neural | 36.26 ± 1.34 |
| revisiting-heterophily-for-graph-neural | 36.04 ± 0.83 |
| neural-sheaf-diffusion-a-topological | 37.81 ± 1.15 |
| non-local-graph-neural-networks | 31.6 ± 1.0 |
| breaking-the-limit-of-graph-neural-networks | 36.53 ± 0.77 |
| revisiting-heterophily-for-graph-neural | 37.09 ± 1.32 |
| beyond-low-frequency-information-in-graph | 34.82 ± 1.35 |