Node Classification On Non Homophilic 15

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
GESN	68.34 ± 0.86	Addressing Heterophily in Node Classification with Graph Echo State Networks
ClenshawGCN	66.56 ± 0.28	Clenshaw Graph Neural Networks
GloGNN++	66.34 ± 0.29	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACM-GCN+	66.24 ± 0.24	Revisiting Heterophily For Graph Neural Networks
GloGNN	66.19 ± 0.29	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
LINKX	66.06 ± 0.19	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ACM-GCN++	65.943 ± 0.284	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	65.92 ± 0.14	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	65.838 ± 0.153	Revisiting Heterophily For Graph Neural Networks
MixHop	65.64 ± 0.27	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
C&S 2-hop	65.02 ± 0.16	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
C&S 1-hop	64.86 ± 0.27	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
LINK	64.85 ± 0.21	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ACM-GCN	63.92 ± 0.19	Revisiting Heterophily For Graph Neural Networks
L Prop 2-hop	63.88 ± 0.24	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ACMII-GCN	63.73 ± 0.13	Revisiting Heterophily For Graph Neural Networks
GCNJK	63.45 ± 0.22	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GCNII	63.39 ± 0.61	Simple and Deep Graph Convolutional Networks
L Prop 1-hop	62.77 ± 0.24	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GCN	62.18 ± 0.26	Semi-Supervised Classification with Graph Convolutional Networks

0 of 26 row(s) selected.