Node Classification On Pubmed 60 20 20 Random

1:1 Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
GNNDLD	91.95±0.19	GNNDLD: Graph Neural Network with Directional Label Distribution
NHGCN	91.56 ± 0.50	Neighborhood Homophily-Guided Graph Convolutional Network
ACM-Snowball-3	91.44 ± 0.59	Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-3	91.31 ± 0.6	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	90.96 ± 0.62	Revisiting Heterophily For Graph Neural Networks
ACM-Snowball-2	90.81 ± 0.52	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN	90.74 ± 0.5	Revisiting Heterophily For Graph Neural Networks
ACM-GCN	90.66 ± 0.47	Revisiting Heterophily For Graph Neural Networks
Graph-MLP + SAF	90.64 ± 0.46%	The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
ACMII-GCN++	90.63 ± 0.56	Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-2	90.56 ± 0.39	Revisiting Heterophily For Graph Neural Networks
ACM-GCN+	90.46 ± 0.69	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	90.39 ± 0.33	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII*	90.18 ± 0.51	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII	90.12 ± 0.4	Revisiting Heterophily For Graph Neural Networks
GCN+JK	90.09 ± 0.68	Revisiting Heterophily For Graph Neural Networks
Geom-GCN*	90.05	Geom-GCN: Geometric Graph Convolutional Networks
GCNII*	89.98 ± 0.52	Simple and Deep Graph Convolutional Networks
FAGCN	89.98 ± 0.54	Beyond Low-frequency Information in Graph Convolutional Networks
NFGNN	89.89±0.68	Node-oriented Spectral Filtering for Graph Neural Networks

0 of 37 row(s) selected.