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

		Paper Title
ACM-GCN++	86.08 ± 0.43	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	85.95 ± 0.26	Revisiting Heterophily For Graph Neural Networks
GloGNN++	85.74 ± 0.42	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GloGNN	85.57 ± 0.35	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACM-GCN+	85.05 ± 0.19	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	84.95 ± 0.43	Revisiting Heterophily For Graph Neural Networks
LINKX	84.71 ± 0.52	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
MixHop	83.47 ± 0.71	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
GCNII	82.92 ± 0.59	Simple and Deep Graph Convolutional Networks
ACM-GCN	82.73 ± 0.52	Revisiting Heterophily For Graph Neural Networks
GCN	82.47 ± 0.27	Semi-Supervised Classification with Graph Convolutional Networks
ACMII-GCN	82.4 ± 0.48	Revisiting Heterophily For Graph Neural Networks
GCNJK	81.63 ± 0.54	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GAT	81.53 ± 0.55	Graph Attention Networks
GPRGCN	81.38 ± 0.16	Adaptive Universal Generalized PageRank Graph Neural Network
H2GCN	81.31 ± 0.60	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
LINK	80.79 ± 0.49	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GATJK	80.69 ± 0.36	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GESN	80.29 ± 0.41	Addressing Heterophily in Node Classification with Graph Echo State Networks
C&S 2-hop	78.40 ± 3.12	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

0 of 28 row(s) selected.