Node Classification On Cora 60 20 20 Random

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

		Paper Title	Repository
GNNDLD	92.99 ±0.9	GNNDLD: Graph Neural Network with Directional Label Distribution	-
ACM-GCN+	89.75 ± 1.16	Revisiting Heterophily For Graph Neural Networks
ACM-Snowball-3	89.59 ± 1.58	Revisiting Heterophily For Graph Neural Networks
GAT+JK	89.52 ± 0.43	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	89.47 ± 1.08	Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-3	89.36 ± 1.26	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	89.33 ± 0.81	Revisiting Heterophily For Graph Neural Networks
Snowball-3	89.33 ± 1.3	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
ACMII-GCN+	89.18 ± 1.11	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII	89.1 ± 1.61	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII*	89.00 ± 1.35	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN	89.00 ± 0.72	Revisiting Heterophily For Graph Neural Networks
GCNII	88.98 ± 1.33	Simple and Deep Graph Convolutional Networks
ACMII-Snowball-2	88.95 ± 1.04	Revisiting Heterophily For Graph Neural Networks
GCNII*	88.93 ± 1.37	Simple and Deep Graph Convolutional Networks
FAGCN	88.85 ± 1.36	Beyond Low-frequency Information in Graph Convolutional Networks
ACM-Snowball-2	88.83 ± 1.49	Revisiting Heterophily For Graph Neural Networks
Snowball-2	88.64 ± 1.15	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
BernNet	88.52 ± 0.95	BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
GCN	87.78 ± 0.96	Semi-Supervised Classification with Graph Convolutional Networks

0 of 33 row(s) selected.