Node Classification On Non Homophilic 15
Métriques
1:1 Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | 1:1 Accuracy |
|---|---|
| large-scale-learning-on-non-homophilous | 60.92 ± 0.07 |
| mixhop-higher-order-graph-convolution | 65.64 ± 0.27 |
| simplifying-graph-convolutional-networks | 59.94 ± 0.21 |
| revisiting-heterophily-for-graph-neural | 66.24 ± 0.24 |
| addressing-heterophily-in-node-classification | 68.34 ± 0.86 |
| revisiting-heterophily-for-graph-neural | 65.92 ± 0.14 |
| finding-global-homophily-in-graph-neural | 66.34 ± 0.29 |
| simplifying-graph-convolutional-networks | 58.97 ± 0.19 |
| revisiting-heterophily-for-graph-neural | 65.943 ± 0.284 |
| semi-supervised-classification-with-graph | 62.18 ± 0.26 |
| joint-adaptive-feature-smoothing-and-topology | 61.89 ± 0.29 |
| large-scale-learning-on-non-homophilous | 62.77 ± 0.24 |
| predict-then-propagate-graph-neural-networks | 60.97 ± 0.10 |
| large-scale-learning-on-non-homophilous | 63.45 ± 0.22 |
| combining-label-propagation-and-simple-models-1 | 64.86 ± 0.27 |
| combining-label-propagation-and-simple-models-1 | 65.02 ± 0.16 |
| finding-global-homophily-in-graph-neural | 66.19 ± 0.29 |
| revisiting-heterophily-for-graph-neural | 63.92 ± 0.19 |
| large-scale-learning-on-non-homophilous | 66.06 ± 0.19 |
| clenshaw-graph-neural-networks | 66.56 ± 0.28 |
| large-scale-learning-on-non-homophilous | 59.98 ± 2.87 |
| simple-and-deep-graph-convolutional-networks-1 | 63.39 ± 0.61 |
| revisiting-heterophily-for-graph-neural | 63.73 ± 0.13 |
| revisiting-heterophily-for-graph-neural | 65.838 ± 0.153 |
| large-scale-learning-on-non-homophilous | 63.88 ± 0.24 |
| large-scale-learning-on-non-homophilous | 64.85 ± 0.21 |