HyperAIHyperAI

Command Palette

Search for a command to run...

Plateforme

Node Classification On Pubmed 48 32 20 Fixed

Métriques

1:1 Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Paper Title
GCNII90.15 ± 0.43Simple and Deep Graph Convolutional Networks
Geom-GCN89.95 ± 0.47Geom-GCN: Geometric Graph Convolutional Networks
ACMII-GCN89.89 ± 0.43Revisiting Heterophily For Graph Neural Networks
ACM-GCN+89.82 ± 0.41Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+89.78 ± 0.49Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++89.71 ± 0.48Revisiting Heterophily For Graph Neural Networks
ACM-GCN++89.65 ± 0.58Revisiting Heterophily For Graph Neural Networks
GloGNN89.62 ± 0.35Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
O(d)-NSD89.49 ± 0.40Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
H2GCN89.49 ± 0.38Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Diag-NSD89.42 ± 0.43Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Gen-NSD89.33 ± 0.35Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
GloGNN++89.24 ± 0.39Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GESN89.20 ± 0.34Addressing Heterophily in Node Classification with Graph Echo State Networks
GGCN89.15 ± 0.37Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
ACM-SGC-289.01 ± 0.6Revisiting Heterophily For Graph Neural Networks
NLGCN 89.0 ± 0.5Non-Local Graph Neural Networks
WRGAT88.52 ± 0.92Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
ACM-SGC-188.49 ± 0.51Revisiting Heterophily For Graph Neural Networks
NLGAT 88.2 ± 0.3Non-Local Graph Neural Networks
0 of 26 row(s) selected.