The node importance evaluation method based on graph convolution in multilayer heterogeneous networks

Node importance evaluation is a hot issue in complex network analysis. Existing node importance evaluation methods are mainly oriented to homogeneous networks, which ignore the heterogeneity of node types and edges. We propose an MLN critical node evaluation method based on graph convolution. In thi...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhixing Chen, Jian Shu, Linlan Liu
Format: Article
Language:English
Published: Taylor & Francis Group 2023-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2023.2229964
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255860747468800
author Zhixing Chen
Jian Shu
Linlan Liu
author_facet Zhixing Chen
Jian Shu
Linlan Liu
author_sort Zhixing Chen
collection DOAJ
description Node importance evaluation is a hot issue in complex network analysis. Existing node importance evaluation methods are mainly oriented to homogeneous networks, which ignore the heterogeneity of node types and edges. We propose an MLN critical node evaluation method based on graph convolution. In this paper, we generate the feature matrix of nodes. Considering the diversity of node types in the network, we design an adapted node sampling method based on the meta path. An MLN node embedding model is constructed based on a graph convolutional network (MGC). Besides, the negative sampling technique is used to complete MGC training. Metrics of critical node evaluation are constructed by combining the node embedding vectors and local structural features to evaluate the node's importance. The experimental results show that the proposed method has better evaluation accuracy than the K-Shell algorithm (K-Shell), K-shell-based gravity model ranking algorithm (KSDG), the Page Rank algorithm in MLN (PR), influence maximization based on network embedding (IMNE) and the node ranking algorithm based on information entropy (ERM).
format Article
id doaj-art-4c844532c5f042eca7996c4e5d93417d
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2023-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-4c844532c5f042eca7996c4e5d93417d2025-08-20T01:56:46ZengTaylor & Francis GroupConnection Science0954-00911360-04942023-12-0135110.1080/09540091.2023.22299642229964The node importance evaluation method based on graph convolution in multilayer heterogeneous networksZhixing Chen0Jian Shu1Linlan Liu2Nanchang Hangkong UniversityNanchang Hangkong UniversityNanchang Hangkong UniversityNode importance evaluation is a hot issue in complex network analysis. Existing node importance evaluation methods are mainly oriented to homogeneous networks, which ignore the heterogeneity of node types and edges. We propose an MLN critical node evaluation method based on graph convolution. In this paper, we generate the feature matrix of nodes. Considering the diversity of node types in the network, we design an adapted node sampling method based on the meta path. An MLN node embedding model is constructed based on a graph convolutional network (MGC). Besides, the negative sampling technique is used to complete MGC training. Metrics of critical node evaluation are constructed by combining the node embedding vectors and local structural features to evaluate the node's importance. The experimental results show that the proposed method has better evaluation accuracy than the K-Shell algorithm (K-Shell), K-shell-based gravity model ranking algorithm (KSDG), the Page Rank algorithm in MLN (PR), influence maximization based on network embedding (IMNE) and the node ranking algorithm based on information entropy (ERM).http://dx.doi.org/10.1080/09540091.2023.2229964multi-layer networkcritical node evaluationgraph convolutionmeta path
spellingShingle Zhixing Chen
Jian Shu
Linlan Liu
The node importance evaluation method based on graph convolution in multilayer heterogeneous networks
Connection Science
multi-layer network
critical node evaluation
graph convolution
meta path
title The node importance evaluation method based on graph convolution in multilayer heterogeneous networks
title_full The node importance evaluation method based on graph convolution in multilayer heterogeneous networks
title_fullStr The node importance evaluation method based on graph convolution in multilayer heterogeneous networks
title_full_unstemmed The node importance evaluation method based on graph convolution in multilayer heterogeneous networks
title_short The node importance evaluation method based on graph convolution in multilayer heterogeneous networks
title_sort node importance evaluation method based on graph convolution in multilayer heterogeneous networks
topic multi-layer network
critical node evaluation
graph convolution
meta path
url http://dx.doi.org/10.1080/09540091.2023.2229964
work_keys_str_mv AT zhixingchen thenodeimportanceevaluationmethodbasedongraphconvolutioninmultilayerheterogeneousnetworks
AT jianshu thenodeimportanceevaluationmethodbasedongraphconvolutioninmultilayerheterogeneousnetworks
AT linlanliu thenodeimportanceevaluationmethodbasedongraphconvolutioninmultilayerheterogeneousnetworks
AT zhixingchen nodeimportanceevaluationmethodbasedongraphconvolutioninmultilayerheterogeneousnetworks
AT jianshu nodeimportanceevaluationmethodbasedongraphconvolutioninmultilayerheterogeneousnetworks
AT linlanliu nodeimportanceevaluationmethodbasedongraphconvolutioninmultilayerheterogeneousnetworks