Node Classification On Film 60 20 20 Random

1:1 Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
GNNDLD	75.69±0.78	GNNDLD: Graph Neural Network with Directional Label Distribution
NHGCN	43.94 ± 1.14	Neighborhood Homophily-Guided Graph Convolutional Network
FavardGNN	43.05 ± 0.53	Graph Neural Networks with Learnable and Optimal Polynomial Bases
OptBasisGNN	42.39 ± 0.52	Graph Neural Networks with Learnable and Optimal Polynomial Bases
ACM-GCN++	41.86 ± 1.48	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN	41.84 ± 1.15	Revisiting Heterophily For Graph Neural Networks
ACM-GCN+	41.79 ± 1.01	Revisiting Heterophily For Graph Neural Networks
BernNet	41.79 ± 1.01	BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
ACMII-GCN++	41.66 ± 1.42	Revisiting Heterophily For Graph Neural Networks
GCNII*	41.54 ± 0.99	Simple and Deep Graph Convolutional Networks
ACMII-GCN+	41.5 ± 1.54	Revisiting Heterophily For Graph Neural Networks
ACM-Snowball-2	41.4 ± 1.23	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII	41.37 ± 1.37	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII*	41.27 ± 1.24	Revisiting Heterophily For Graph Neural Networks
ACM-Snowball-3	41.27 ± 0.8	Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-2	41.1 ± 0.75	Revisiting Heterophily For Graph Neural Networks
GCNII	40.82 ± 1.79	Simple and Deep Graph Convolutional Networks
ACMII-Snowball-3	40.31 ± 1.6	Revisiting Heterophily For Graph Neural Networks
ACM-SGC-2	40.13 ± 1.21	Revisiting Heterophily For Graph Neural Networks
ACM-SGC-1	39.33 ± 1.25	Revisiting Heterophily For Graph Neural Networks

0 of 37 row(s) selected.