Node Classification On Non Homophilic 2

Métriques

1:1 Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Tableau comparatif

Nom du modèle	1:1 Accuracy
revisiting-heterophily-for-graph-neural	93.61 ± 1.55
mixhop-higher-order-graph-convolution	76.39 ± 7.66
inductive-representation-learning-on-large	79.03 ± 1.20
revisiting-heterophily-for-graph-neural	92.46 ± 1.97
break-the-ceiling-stronger-multi-scale-deep	83.11 ± 3.2
simplifying-graph-convolutional-networks	81.31 ± 3.3
beyond-low-frequency-information-in-graph	88.85 ± 4.39
geom-gcn-geometric-graph-convolutional-1	67.57
revisiting-heterophily-for-graph-neural	96.56 ± 2
revisiting-heterophily-for-graph-neural	95.41 ± 2.82
revisiting-heterophily-for-graph-neural	94.75 ± 2.91
revisiting-heterophily-for-graph-neural	94.75 ± 3.09
revisiting-heterophily-for-graph-neural	95.25 ± 1.55
revisiting-heterophily-for-graph-neural	94.92 ± 2.79
simplifying-graph-convolutional-networks	83.28 ± 5.43
generalizing-graph-neural-networks-beyond	85.90 ± 3.53
simple-and-deep-graph-convolutional-networks-1	88.52 ± 3.02
simple-and-deep-graph-convolutional-networks-1	82.46 ± 4.58
predict-then-propagate-graph-neural-networks	91.18 ± 0.70
revisiting-heterophily-for-graph-neural	80.66 ± 1.91
semi-supervised-classification-with-graph	83.11 ± 3.2
joint-adaptive-feature-smoothing-and-topology	92.26 ± 0.71
bernnet-learning-arbitrary-graph-spectral	93.12 ± 0.65
revisiting-heterophily-for-graph-neural	93.44 ± 2.54
graph-attention-networks	78.87 ± 0.86
revisiting-heterophily-for-graph-neural	95.08 ± 2.07
break-the-ceiling-stronger-multi-scale-deep	83.11 ± 3.2
revisiting-heterophily-for-graph-neural	93.28 ± 2.79
joint-adaptive-feature-smoothing-and-topology	92.92 ± 0.61
revisiting-heterophily-for-graph-neural	75.41 ± 7.18
revisiting-heterophily-for-graph-neural	95.74 ± 2.22
revisiting-heterophily-for-graph-neural	94.75 ± 2.41