Node Classification On Non Homophilic 13

评估指标

1:1 Accuracy

评测结果

各个模型在此基准测试上的表现结果

比较表格

模型名称	1:1 Accuracy
large-scale-learning-on-non-homophilous	84.71 ± 0.52
large-scale-learning-on-non-homophilous	81.63 ± 0.54
revisiting-heterophily-for-graph-neural	82.73 ± 0.52
graph-attention-networks	81.53 ± 0.55
breaking-the-limit-of-graph-neural-networks	74.32 ± 0.53
predict-then-propagate-graph-neural-networks	74.33 ± 0.38
combining-label-propagation-and-simple-models-1	74.28 ± 1.19
large-scale-learning-on-non-homophilous	74.13 ± 0.46
revisiting-heterophily-for-graph-neural	85.95 ± 0.26
mixhop-higher-order-graph-convolution	83.47 ± 0.71
large-scale-learning-on-non-homophilous	80.69 ± 0.36
finding-global-homophily-in-graph-neural	85.57 ± 0.35
generalizing-graph-neural-networks-beyond	81.31 ± 0.60
combining-label-propagation-and-simple-models-1	78.40 ± 3.12
revisiting-heterophily-for-graph-neural	73.61 ± 0.40
revisiting-heterophily-for-graph-neural	84.95 ± 0.43
large-scale-learning-on-non-homophilous	80.79 ± 0.49
simplifying-graph-convolutional-networks	76.09 ± 0.45
revisiting-heterophily-for-graph-neural	85.05 ± 0.19
finding-global-homophily-in-graph-neural	85.74 ± 0.42
simple-and-deep-graph-convolutional-networks-1	82.92 ± 0.59
semi-supervised-classification-with-graph	82.47 ± 0.27
joint-adaptive-feature-smoothing-and-topology	81.38 ± 0.16
large-scale-learning-on-non-homophilous	63.21 ± 0.39
addressing-heterophily-in-node-classification	80.29 ± 0.41
revisiting-heterophily-for-graph-neural	86.08 ± 0.43
simplifying-graph-convolutional-networks	66.79 ± 0.27
revisiting-heterophily-for-graph-neural	82.4 ± 0.48