Semi-Supervised Classification of Graph Convolutional Networks with Laplacian Rank Constraints

Graph convolutional networks (GCNs), as an extension of classic convolutional neural networks (CNNs) in graph processing, have achieved good results in completing semi-supervised learning tasks. Traditional GCNs usually use fixed graph to complete various semi-supervised classification tasks, such a...

Full description

Saved in:
Bibliographic Details
Published inNeural processing letters Vol. 54; no. 4; pp. 2645 - 2656
Main Authors Zhang, Haiqi, Lu, Guangquan, Zhan, Mengmeng, Zhang, Beixian
Format Journal Article
LanguageEnglish
Published New York Springer US 01.08.2022
Springer Nature B.V
Subjects
Artificial Intelligence
Artificial neural networks
Classification
Cognitive tasks
Complex Systems
Computational Intelligence
Computer Science
Decision trees
Decomposition
Eigenvalues
Eigenvectors
Fourier transforms
Graph representations
Machine learning
Methods
Neural networks
Polynomials
Semi-supervised learning
Similarity
Social networks
Support vector machines
Topology
Graph learning
Semi-supervised classification
Rank constraint
Graph convolutional networks
Online AccessGet full text

Cover

More Information
Summary:Graph convolutional networks (GCNs), as an extension of classic convolutional neural networks (CNNs) in graph processing, have achieved good results in completing semi-supervised learning tasks. Traditional GCNs usually use fixed graph to complete various semi-supervised classification tasks, such as chemical molecules and social networks. Graph is an important basis for the classification of GCNs model, and its quality has a large impact on the performance of the model. For low-quality input graph, the classification results of the GCNs model are often not ideal. In order to improve the classification effect of GCNs model, we propose a graph learning method to generate high-quality topological graph, which is more suitable for GCNs model classification. We use the correlation between the data to generate a data similarity matrix, and apply Laplacian rank constraint to similarity matrix, so that the number of connected components of the topological graph is consistent with the number of categories of the original data. Experimental results on 10 real datasets show that our method is better than the comparison method in classification effect.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1370-4621
1573-773X
DOI:10.1007/s11063-020-10404-7