Node Classification On Non Homophilic 8

평가 지표

1:1 Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	1:1 Accuracy	Paper Title
GPRGCN	82.55 ± 6.23	Adaptive Universal Generalized PageRank Graph Neural Network
NLMLP	87.3 ± 4.3	Non-Local Graph Neural Networks
ACMII-GCN++	88.43 ± 3.66	Revisiting Heterophily For Graph Neural Networks
ACM-SGC-1	86.47 ± 3.77	Revisiting Heterophily For Graph Neural Networks
GloGNN++	88.04 ± 3.22	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
FAGCN	79.61 ± 1.58	Beyond Low-frequency Information in Graph Convolutional Networks
ACM-GCN+	88.43 ± 2.39	Revisiting Heterophily For Graph Neural Networks
LINKX	75.49 ± 5.72	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GESN	83.33 ± 3.81	Addressing Heterophily in Node Classification with Graph Echo State Networks
GCNII	80.39 ± 3.40	Simple and Deep Graph Convolutional Networks
MixHop	75.88 ± 4.90	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Geom-GCN	64.51 ± 3.66	Geom-GCN: Geometric Graph Convolutional Networks
GGCN	86.86 ± 3.29	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
ACM-SGC-2	86.47 ± 3.77	Revisiting Heterophily For Graph Neural Networks
O(d)-NSD	89.41 ± 4.74	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
NLGCN	60.2 ± 5.3	Non-Local Graph Neural Networks
H2GCN	87.65 ± 4.98	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Diag-NSD	88.63 ± 2.75	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
WRGAT	86.98 ± 3.78	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
ACM-GCN	88.43 ± 3.22	Revisiting Heterophily For Graph Neural Networks

0 of 26 row(s) selected.