Node Classification On Non Homophilic 14
Metriken
1:1 Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | 1:1 Accuracy |
|---|---|
| combining-label-propagation-and-simple-models-1 | 84.94 ± 0.49 |
| large-scale-learning-on-non-homophilous | 56.70 ± 2.07 |
| semi-supervised-classification-with-graph | 87.42 ± 0.37 |
| clenshaw-graph-neural-networks | 91.69 ± 0.25 |
| finding-global-homophily-in-graph-neural | 90.66 ± 0.11 |
| mixhop-higher-order-graph-convolution | 90.58 ± 0.16 |
| joint-adaptive-feature-smoothing-and-topology | 90.05 ± 0.31 |
| large-scale-learning-on-non-homophilous | 86.68 ± 0.09 |
| revisiting-heterophily-for-graph-neural | 91.33 ± 0.11 |
| graph-neural-networks-with-learnable-and | 90.83±0.11 |
| large-scale-learning-on-non-homophilous | 73.56 ± 0.14 |
| revisiting-heterophily-for-graph-neural | 91.4 ± 0.07 |
| revisiting-heterophily-for-graph-neural | 91.13 ± 0.09 |
| simplifying-graph-convolutional-networks | 82.10 ± 0.14 |
| predict-then-propagate-graph-neural-networks | 85.36 ± 0.62 |
| finding-global-homophily-in-graph-neural | 90.91 ± 0.13 |
| revisiting-heterophily-for-graph-neural | 91.01 ± 0.18 |
| simple-and-deep-graph-convolutional-networks-1 | 90.24 ± 0.09 |
| revisiting-heterophily-for-graph-neural | 91.44 ± 0.08 |
| large-scale-learning-on-non-homophilous | 67.04 ± 0.20 |
| simplifying-graph-convolutional-networks | 82.36 ± 0.37 |
| large-scale-learning-on-non-homophilous | 89.30 ± 0.19 |
| revisiting-heterophily-for-graph-neural | 91.19 ± 0.16 |
| large-scale-learning-on-non-homophilous | 90.77 ± 0.27 |
| large-scale-learning-on-non-homophilous | 66.02 ± 0.16 |
| combining-label-propagation-and-simple-models-1 | 82.93 ± 0.15 |