Node Classification On Non Homophilic 8
Metriken
1:1 Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | 1:1 Accuracy |
|---|---|
| joint-adaptive-feature-smoothing-and-topology | 82.55 ± 6.23 |
| non-local-graph-neural-networks | 87.3 ± 4.3 |
| revisiting-heterophily-for-graph-neural | 88.43 ± 3.66 |
| revisiting-heterophily-for-graph-neural | 86.47 ± 3.77 |
| finding-global-homophily-in-graph-neural | 88.04 ± 3.22 |
| beyond-low-frequency-information-in-graph | 79.61 ± 1.58 |
| revisiting-heterophily-for-graph-neural | 88.43 ± 2.39 |
| large-scale-learning-on-non-homophilous | 75.49 ± 5.72 |
| addressing-heterophily-in-node-classification | 83.33 ± 3.81 |
| simple-and-deep-graph-convolutional-networks-1 | 80.39 ± 3.40 |
| mixhop-higher-order-graph-convolution | 75.88 ± 4.90 |
| geom-gcn-geometric-graph-convolutional-1 | 64.51 ± 3.66 |
| two-sides-of-the-same-coin-heterophily-and | 86.86 ± 3.29 |
| revisiting-heterophily-for-graph-neural | 86.47 ± 3.77 |
| neural-sheaf-diffusion-a-topological | 89.41 ± 4.74 |
| non-local-graph-neural-networks | 60.2 ± 5.3 |
| generalizing-graph-neural-networks-beyond | 87.65 ± 4.98 |
| neural-sheaf-diffusion-a-topological | 88.63 ± 2.75 |
| breaking-the-limit-of-graph-neural-networks | 86.98 ± 3.78 |
| revisiting-heterophily-for-graph-neural | 88.43 ± 3.22 |
| revisiting-heterophily-for-graph-neural | 87.45 ± 3.74 |
| non-local-graph-neural-networks | 56.9 ± 7.3 |
| finding-global-homophily-in-graph-neural | 87.06 ± 3.53 |
| revisiting-heterophily-for-graph-neural | 88.24 ± 3.16 |
| neural-sheaf-diffusion-a-topological | 89.21 ± 3.84 |
| revisiting-heterophily-for-graph-neural | 88.04 ± 3.66 |