Node Classification On Non Homophilic 6

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
ACMII-GCN+++	67.5±0.53	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	67.44±0.31	Revisiting Heterophily For Graph Neural Networks
ACM-GCN+	67.4±0.44	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	67.3±0.48	Revisiting Heterophily For Graph Neural Networks
H2GCN	67.22±0.90	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
APPNP	67.21±0.56	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
ACMII-GCN	67.15±0.41	Revisiting Heterophily For Graph Neural Networks
ACM-GCN	67.01±0.38	Revisiting Heterophily For Graph Neural Networks
GPRGNN	66.90±0.50	Adaptive Universal Generalized PageRank Graph Neural Network
FAGCN	66.86±0.53	Beyond Low-frequency Information in Graph Convolutional Networks
MixHop	66.80±0.58	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
ACM-SGC-1	66.67±0.56	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII*	66.6±0.57	Revisiting Heterophily For Graph Neural Networks
MLP-2	66.55±0.72	New Benchmarks for Learning on Non-Homophilous Graphs
ACM-SGC-2	66.53±0.57	Revisiting Heterophily For Graph Neural Networks
GCNII*	66.42±0.56	Simple and Deep Graph Convolutional Networks
ACM-GCNII	66.39±0.56	Revisiting Heterophily For Graph Neural Networks
GCNII	66.38±0.45	Simple and Deep Graph Convolutional Networks
C&S(1hop)	64.60±0.57	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
C&S(2hop)	64.52±0.62	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

0 of 28 row(s) selected.