Robust graph learning with graph convolutional network

Graph convolutional network (GCN) is a powerful tool to process the graph data and has achieved satisfactory performance in the task of node classification. In general, GCN uses a fixed graph to guide the graph convolutional operation. However, the fixed graph from the original feature space may con...

Full description

Saved in:
Bibliographic Details
Published in:Information processing & management 2022-05, Vol.59 (3), p.102916, Article 102916
Main Authors: Wan, Yingying, Yuan, Changan, Zhan, Mengmeng, Chen, Long
Format: Article
Language:English
Subjects:
Artificial neural networks
Classification
Constraint modelling
Data processing
Graph convolutional network
Graphs
Learning
Mathematical models
Node classification
Outliers (statistics)
Robustness
Smoothness
Sparse constraint
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Graph convolutional network (GCN) is a powerful tool to process the graph data and has achieved satisfactory performance in the task of node classification. In general, GCN uses a fixed graph to guide the graph convolutional operation. However, the fixed graph from the original feature space may contain noises or outliers, which may degrade the effectiveness of GCN. To address this issue, in this paper, we propose a robust graph learning convolutional network (RGLCN). Specifically, we design a robust graph learning model based on the sparse constraint and strong connectivity constraint to achieve the smoothness of the graph learning. In addition, we introduce graph learning model into GCN to explore the representative information, aiming to learning a high-quality graph for the downstream task. Experiments on citation network datasets show that the proposed RGLCN outperforms the existing comparison methods with respect to the task of node classification.
ISSN:0306-4573
1873-5371
DOI:10.1016/j.ipm.2022.102916