Node Classification On Cora 48 32 20 Fixed

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
NLGAT	88.5 ± 1.8	Non-Local Graph Neural Networks
GCNII	88.37 ± 1.25	Simple and Deep Graph Convolutional Networks
GloGNN++	88.33 ± 1.09	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GloGNN	88.31 ± 1.13	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACMII-GCN++	88.25 ± 0.96	Revisiting Heterophily For Graph Neural Networks
WRGAT	88.20 ± 2.26	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
ACMII-GCN+	88.19 ± 1.17	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	88.11 ± 0.96	Revisiting Heterophily For Graph Neural Networks
NLGCN	88.1 ± 1.0	Non-Local Graph Neural Networks
FAGCN	88.05 ± 1.57	Beyond Low-frequency Information in Graph Convolutional Networks
ACM-GCN+	88.05 ± 0.99	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN	88.01 ± 1.08	Revisiting Heterophily For Graph Neural Networks
GGCN	87.95 ± 1.05	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
GPRGCN	87.95 ± 1.18	Adaptive Universal Generalized PageRank Graph Neural Network
H2GCN	87.87 ± 1.20	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
ACM-SGC-2	87.69 ± 1.07	Revisiting Heterophily For Graph Neural Networks
MixHop	87.61 ± 0.85	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Gen-NSD	87.30 ± 1.15	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Diag-NSD	87.14 ± 1.06	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
ACM-SGC-1	86.9 ± 1.38	Revisiting Heterophily For Graph Neural Networks

0 of 26 row(s) selected.