Node Classification On Non Homophilic 7

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
ACM-GCN+	85.68 ± 4.84	Revisiting Heterophily For Graph Neural Networks
MixHop	73.51 ± 6.34	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
NLMLP	84.9 ± 5.7	Non-Local Graph Neural Networks
ACM-SGC-2	82.43 ± 5.44	Revisiting Heterophily For Graph Neural Networks
NLGCN	57.6 ± 5.5	Non-Local Graph Neural Networks
Deformable GCN	85.95±4.37	Deformable Graph Convolutional Networks
LINKX	77.84 ± 5.81	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ACMII-GCN++	86.49 ± 6.73	Revisiting Heterophily For Graph Neural Networks
WRGAT	81.62 ±3.90	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
FAGCN	76.76 ± 5.87	Beyond Low-frequency Information in Graph Convolutional Networks
NLGAT	54.7 ± 7.6	Non-Local Graph Neural Networks
H2GCN	82.70 ± 5.28	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
GCNII	77.86 ± 3.79	Simple and Deep Graph Convolutional Networks
Geom-GCN	60.54 ± 3.67	Geom-GCN: Geometric Graph Convolutional Networks
Gen-NSD	85.68 ± 6.51	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
ACM-SGC-1	82.43 ± 5.44	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN	85.95 ± 5.64	Revisiting Heterophily For Graph Neural Networks
GGCN	85.68 ± 6.63	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
GloGNN++	85.95 ± 5.10	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACMII-GCN+	85.41 ± 5.3	Revisiting Heterophily For Graph Neural Networks

0 of 27 row(s) selected.