A generative probabilistic classifier using node text, in/out-degree, and first-order neighbor-label counts achieves competitive accuracy on the Math Genealogy and ogbn-arxiv datasets.
Ap- plications of graph convolutional networks in computer vision.Neural Com- puting and Applications , 34(16):13387–13405, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
A Probabilistic Model for Node Classification in Directed Graphs
A generative probabilistic classifier using node text, in/out-degree, and first-order neighbor-label counts achieves competitive accuracy on the Math Genealogy and ogbn-arxiv datasets.