Node Classification On Non Homophilic 9
Métriques
1:1 Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | 1:1 Accuracy |
|---|---|
| non-local-graph-neural-networks | 85.4 ± 3.8 |
| joint-adaptive-feature-smoothing-and-topology | 81.35 ± 5.32 |
| geom-gcn-geometric-graph-convolutional-1 | 66.76 ± 2.72 |
| breaking-the-limit-of-graph-neural-networks | 83.62 ± 5.50 |
| revisiting-heterophily-for-graph-neural | 88.38 ± 3.43 |
| revisiting-heterophily-for-graph-neural | 81.89 ± 4.53 |
| beyond-low-frequency-information-in-graph | 84.86 ± 7.23 |
| large-scale-learning-on-non-homophilous | 74.60 ± 8.37 |
| neural-sheaf-diffusion-a-topological | 82.97 ± 5.13 |
| two-sides-of-the-same-coin-heterophily-and | 84.86 ± 4.55 |
| simple-and-deep-graph-convolutional-networks-1 | 77.57 ± 3.83 |
| neural-sheaf-diffusion-a-topological | 85.95 ± 5.51 |
| mixhop-higher-order-graph-convolution | 77.84 ± 7.73 |
| finding-global-homophily-in-graph-neural | 84.05 ± 4.90 |
| revisiting-heterophily-for-graph-neural | 88.38 ± 3.64 |
| neural-sheaf-diffusion-a-topological | 85.67 ± 6.95 |
| revisiting-heterophily-for-graph-neural | 88.11 ± 3.24 |
| revisiting-heterophily-for-graph-neural | 87.84 ± 4.4 |
| revisiting-heterophily-for-graph-neural | 81.89 ± 4.53 |
| addressing-heterophily-in-node-classification | 84.31 ± 4.44 |
| non-local-graph-neural-networks | 62.6 ± 7.1 |
| revisiting-heterophily-for-graph-neural | 88.38 ± 3.43 |
| revisiting-heterophily-for-graph-neural | 86.76 ± 4.75 |
| finding-global-homophily-in-graph-neural | 84.32 ± 4.15 |
| non-local-graph-neural-networks | 65.5 ± 6.6 |
| beyond-low-frequency-information-in-graph | 76.49 ± 2.87 |