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

模型名称	1:1 Accuracy	Paper Title
LINKX	84.71 ± 0.52	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GCNJK	81.63 ± 0.54	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ACM-GCN	82.73 ± 0.52	Revisiting Heterophily For Graph Neural Networks
GAT	81.53 ± 0.55	Graph Attention Networks
WRGAT	74.32 ± 0.53	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
APPNP	74.33 ± 0.38	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
C&S 1-hop	74.28 ± 1.19	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
L Prop 2-hop	74.13 ± 0.46	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ACMII-GCN++	85.95 ± 0.26	Revisiting Heterophily For Graph Neural Networks
MixHop	83.47 ± 0.71	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
GATJK	80.69 ± 0.36	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GloGNN	85.57 ± 0.35	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
H2GCN	81.31 ± 0.60	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
C&S 2-hop	78.40 ± 3.12	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
MLP	73.61 ± 0.40	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	84.95 ± 0.43	Revisiting Heterophily For Graph Neural Networks
LINK	80.79 ± 0.49	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
SGC 2-hop	76.09 ± 0.45	Simplifying Graph Convolutional Networks
ACM-GCN+	85.05 ± 0.19	Revisiting Heterophily For Graph Neural Networks
GloGNN++	85.74 ± 0.42	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

0 of 28 row(s) selected.