Node Classification On Non Homophilic 9

평가 지표

1:1 Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	1:1 Accuracy	Paper Title
NLMLP	85.4 ± 3.8	Non-Local Graph Neural Networks
GPRGCN	81.35 ± 5.32	Adaptive Universal Generalized PageRank Graph Neural Network
Geom-GCN	66.76 ± 2.72	Geom-GCN: Geometric Graph Convolutional Networks
WRGAT	83.62 ± 5.50	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
ACM-GCN++	88.38 ± 3.43	Revisiting Heterophily For Graph Neural Networks
ACM-SGC-2	81.89 ± 4.53	Revisiting Heterophily For Graph Neural Networks
H2GCN	84.86 ± 7.23	Beyond Low-frequency Information in Graph Convolutional Networks
LINKX	74.60 ± 8.37	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Gen-NSD	82.97 ± 5.13	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
GGCN	84.86 ± 4.55	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
GCNII	77.57 ± 3.83	Simple and Deep Graph Convolutional Networks
O(d)-NSD	85.95 ± 5.51	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
MixHop	77.84 ± 7.73	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
GloGNN++	84.05 ± 4.90	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACM-GCN+	88.38 ± 3.64	Revisiting Heterophily For Graph Neural Networks
Diag-NSD	85.67 ± 6.95	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
ACMII-GCN+	88.11 ± 3.24	Revisiting Heterophily For Graph Neural Networks
ACM-GCN	87.84 ± 4.4	Revisiting Heterophily For Graph Neural Networks
ACM-SGC-1	81.89 ± 4.53	Revisiting Heterophily For Graph Neural Networks
GESN	84.31 ± 4.44	Addressing Heterophily in Node Classification with Graph Echo State Networks

0 of 26 row(s) selected.