Node Classification On Citeseer 48 32 20

Metrics

1:1 Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
Geom-GCN	78.02 ± 1.15	Geom-GCN: Geometric Graph Convolutional Networks
ACM-GCN+	77.67 ± 1.19	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	77.46 ± 1.65	Revisiting Heterophily For Graph Neural Networks
GloGNN	77.41 ± 1.65	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GCNII	77.33 ± 1.48	Simple and Deep Graph Convolutional Networks
GloGNN++	77.22 ± 1.78	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACMII-GCN+	77.2 ± 1.61	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN	77.15 ± 1.45	Revisiting Heterophily For Graph Neural Networks
Diag-NSD	77.14 ± 1.85	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
GGCN	77.14 ± 1.45	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
GPRGCN	77.13 ± 1.67	Adaptive Universal Generalized PageRank Graph Neural Network
ACMII-GCN++	77.12 ± 1.58	Revisiting Heterophily For Graph Neural Networks
H2GCN	77.11 ± 1.57	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
FAGCN	77.07 ± 2.05	Beyond Low-frequency Information in Graph Convolutional Networks
WRGAT	76.81 ± 1.89	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
ACM-SGC-1	76.73 ± 1.59	Revisiting Heterophily For Graph Neural Networks
O(d)-NSD	76.70 ± 1.57	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
ACM-SGC-2	76.59 ± 1.69	Revisiting Heterophily For Graph Neural Networks
Gen-NSD	76.32 ± 1.65	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
MixHop	76.26 ± 1.33	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

0 of 26 row(s) selected.

Command Palette

Node Classification On Citeseer 48 32 20

Metrics

Results