Node Classification On Pubmed 48 32 20 Fixed

Metrics

1:1 Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
GCNII	90.15 ± 0.43	Simple and Deep Graph Convolutional Networks
Geom-GCN	89.95 ± 0.47	Geom-GCN: Geometric Graph Convolutional Networks
ACMII-GCN	89.89 ± 0.43	Revisiting Heterophily For Graph Neural Networks
ACM-GCN+	89.82 ± 0.41	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	89.78 ± 0.49	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	89.71 ± 0.48	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	89.65 ± 0.58	Revisiting Heterophily For Graph Neural Networks
GloGNN	89.62 ± 0.35	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
O(d)-NSD	89.49 ± 0.40	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
H2GCN	89.49 ± 0.38	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Diag-NSD	89.42 ± 0.43	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Gen-NSD	89.33 ± 0.35	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
GloGNN++	89.24 ± 0.39	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GESN	89.20 ± 0.34	Addressing Heterophily in Node Classification with Graph Echo State Networks
GGCN	89.15 ± 0.37	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
ACM-SGC-2	89.01 ± 0.6	Revisiting Heterophily For Graph Neural Networks
NLGCN	89.0 ± 0.5	Non-Local Graph Neural Networks
WRGAT	88.52 ± 0.92	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
ACM-SGC-1	88.49 ± 0.51	Revisiting Heterophily For Graph Neural Networks
NLGAT	88.2 ± 0.3	Non-Local Graph Neural Networks

0 of 26 row(s) selected.

Command Palette

Node Classification On Pubmed 48 32 20 Fixed

Metrics

Results