RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough Graph

The graph convolution neural network uses topological graph to portray inter-node relationships and update node features. However, the traditional topological graph can only describe the certain relationship between nodes (that is, the weight of the connecting edge is a fixed value), while ignoring...

Full description

Saved in:
Bibliographic Details
Main Authors: Weiping Ding, Bairu Pan, Hengrong Ju, Jiashuang Huang, Chun Cheng, Xinjie Shen, Yu Geng, Tao Hou
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9856642/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850066391063855104
author Weiping Ding
Bairu Pan
Hengrong Ju
Jiashuang Huang
Chun Cheng
Xinjie Shen
Yu Geng
Tao Hou
author_facet Weiping Ding
Bairu Pan
Hengrong Ju
Jiashuang Huang
Chun Cheng
Xinjie Shen
Yu Geng
Tao Hou
author_sort Weiping Ding
collection DOAJ
description The graph convolution neural network uses topological graph to portray inter-node relationships and update node features. However, the traditional topological graph can only describe the certain relationship between nodes (that is, the weight of the connecting edge is a fixed value), while ignoring the uncertainty widely existing in the real world. These uncertainties not only affect the relationship between nodes, but also affect the final classification performance of the model. In order to overcome this defect, a graph convolution neural network algorithm based on rough graph is proposed in this paper. Specifically, the algorithm first constructs a rough graph using a combination of the upper and lower approximation theory of the rough set and the edge theory of the topological graph, the paired maximum-minimum relationship values are used to characterize the uncertain relationship between nodes. Then, this paper designs an end-to-end training neural network architecture based on rough graph, the trained rough graph is fed to this neural network to update node features with these uncertain relationship. Finally, nodes are classified according to these learned node features. The experimental results on real data show that the proposed algorithm can significantly improve the accuracy of node classification compared with the traditional graph convolution neural network.
format Article
id doaj-art-0ef883fcb74c4d929c728de68f7680c8
institution DOAJ
issn 2169-3536
language English
publishDate 2022-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-0ef883fcb74c4d929c728de68f7680c82025-08-20T02:48:46ZengIEEEIEEE Access2169-35362022-01-0110855828559410.1109/ACCESS.2022.31987309856642RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough GraphWeiping Ding0https://orcid.org/0000-0002-3180-7347Bairu Pan1Hengrong Ju2https://orcid.org/0000-0001-9894-9844Jiashuang Huang3https://orcid.org/0000-0002-6204-9569Chun Cheng4Xinjie Shen5Yu Geng6Tao Hou7School of Information Science and Technology, Nantong University, Jiangsu, ChinaSchool of Information Science and Technology, Nantong University, Jiangsu, ChinaSchool of Information Science and Technology, Nantong University, Jiangsu, ChinaSchool of Information Science and Technology, Nantong University, Jiangsu, ChinaSchool of Information Science and Technology, Nantong University, Jiangsu, ChinaSchool of Information Science and Technology, Nantong University, Jiangsu, ChinaSchool of Information Science and Technology, Nantong University, Jiangsu, ChinaSchool of Information Science and Technology, Nantong University, Jiangsu, ChinaThe graph convolution neural network uses topological graph to portray inter-node relationships and update node features. However, the traditional topological graph can only describe the certain relationship between nodes (that is, the weight of the connecting edge is a fixed value), while ignoring the uncertainty widely existing in the real world. These uncertainties not only affect the relationship between nodes, but also affect the final classification performance of the model. In order to overcome this defect, a graph convolution neural network algorithm based on rough graph is proposed in this paper. Specifically, the algorithm first constructs a rough graph using a combination of the upper and lower approximation theory of the rough set and the edge theory of the topological graph, the paired maximum-minimum relationship values are used to characterize the uncertain relationship between nodes. Then, this paper designs an end-to-end training neural network architecture based on rough graph, the trained rough graph is fed to this neural network to update node features with these uncertain relationship. Finally, nodes are classified according to these learned node features. The experimental results on real data show that the proposed algorithm can significantly improve the accuracy of node classification compared with the traditional graph convolution neural network.https://ieeexplore.ieee.org/document/9856642/Graph convolution neural networktopological graphrough setrough graphuncertain relationship
spellingShingle Weiping Ding
Bairu Pan
Hengrong Ju
Jiashuang Huang
Chun Cheng
Xinjie Shen
Yu Geng
Tao Hou
RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough Graph
IEEE Access
Graph convolution neural network
topological graph
rough set
rough graph
uncertain relationship
title RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough Graph
title_full RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough Graph
title_fullStr RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough Graph
title_full_unstemmed RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough Graph
title_short RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough Graph
title_sort rg gcn improved graph convolution neural network algorithm based on rough graph
topic Graph convolution neural network
topological graph
rough set
rough graph
uncertain relationship
url https://ieeexplore.ieee.org/document/9856642/
work_keys_str_mv AT weipingding rggcnimprovedgraphconvolutionneuralnetworkalgorithmbasedonroughgraph
AT bairupan rggcnimprovedgraphconvolutionneuralnetworkalgorithmbasedonroughgraph
AT hengrongju rggcnimprovedgraphconvolutionneuralnetworkalgorithmbasedonroughgraph
AT jiashuanghuang rggcnimprovedgraphconvolutionneuralnetworkalgorithmbasedonroughgraph
AT chuncheng rggcnimprovedgraphconvolutionneuralnetworkalgorithmbasedonroughgraph
AT xinjieshen rggcnimprovedgraphconvolutionneuralnetworkalgorithmbasedonroughgraph
AT yugeng rggcnimprovedgraphconvolutionneuralnetworkalgorithmbasedonroughgraph
AT taohou rggcnimprovedgraphconvolutionneuralnetworkalgorithmbasedonroughgraph