MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding

Heterogeneous graph embedding has become a hot topic in network embedding in recent years and has been widely used in lots of practical scenarios. However, most of the existing heterogeneous graph embedding methods cannot make full use of all the auxiliary information. So we proposed a new method ca...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Junhui Chen, Feihu Huang, Jian Peng
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	network embedding heterogeneous graph graph convolution network subgraph decomposition Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/694c78e515ed4c728d316953e42b62f9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:694c78e515ed4c728d316953e42b62f9
record_format	dspace
spelling	oai:doaj.org-article:694c78e515ed4c728d316953e42b62f92021-11-11T14:58:23ZMSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding10.3390/app112198322076-3417https://doaj.org/article/694c78e515ed4c728d316953e42b62f92021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/9832https://doaj.org/toc/2076-3417Heterogeneous graph embedding has become a hot topic in network embedding in recent years and has been widely used in lots of practical scenarios. However, most of the existing heterogeneous graph embedding methods cannot make full use of all the auxiliary information. So we proposed a new method called Multi-Subgraph based Graph Convolution Network (MSGCN), which uses topology information, semantic information, and node feature information to learn node embedding vector. In MSGCN, the graph is firstly decomposed into multiple subgraphs according to the type of edges. Then convolution operation is adopted for each subgraph to obtain the node representations of each subgraph. Finally, the node representations are obtained by aggregating the representation vectors of nodes in each subgraph. Furthermore, we discussed the application of MSGCN with respect to a transductive learning task and inductive learning task, respectively. A node sampling method for inductive learning tasks to obtain representations of new nodes is proposed. This sampling method uses the attention mechanism to find important nodes and then assigns different weights to different nodes during aggregation. We conducted an experiment on three datasets. The experimental results indicate that our MSGCN outperforms the state-of-the-art methods in multi-class node classification tasks.Junhui ChenFeihu HuangJian PengMDPI AGarticlenetwork embeddingheterogeneous graphgraph convolution networksubgraph decompositionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 9832, p 9832 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	network embedding heterogeneous graph graph convolution network subgraph decomposition Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	network embedding heterogeneous graph graph convolution network subgraph decomposition Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Junhui Chen Feihu Huang Jian Peng MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding
description	Heterogeneous graph embedding has become a hot topic in network embedding in recent years and has been widely used in lots of practical scenarios. However, most of the existing heterogeneous graph embedding methods cannot make full use of all the auxiliary information. So we proposed a new method called Multi-Subgraph based Graph Convolution Network (MSGCN), which uses topology information, semantic information, and node feature information to learn node embedding vector. In MSGCN, the graph is firstly decomposed into multiple subgraphs according to the type of edges. Then convolution operation is adopted for each subgraph to obtain the node representations of each subgraph. Finally, the node representations are obtained by aggregating the representation vectors of nodes in each subgraph. Furthermore, we discussed the application of MSGCN with respect to a transductive learning task and inductive learning task, respectively. A node sampling method for inductive learning tasks to obtain representations of new nodes is proposed. This sampling method uses the attention mechanism to find important nodes and then assigns different weights to different nodes during aggregation. We conducted an experiment on three datasets. The experimental results indicate that our MSGCN outperforms the state-of-the-art methods in multi-class node classification tasks.
format	article
author	Junhui Chen Feihu Huang Jian Peng
author_facet	Junhui Chen Feihu Huang Jian Peng
author_sort	Junhui Chen
title	MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding
title_short	MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding
title_full	MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding
title_fullStr	MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding
title_full_unstemmed	MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding
title_sort	msgcn: multi-subgraph based heterogeneous graph convolution network embedding
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/694c78e515ed4c728d316953e42b62f9
work_keys_str_mv	AT junhuichen msgcnmultisubgraphbasedheterogeneousgraphconvolutionnetworkembedding AT feihuhuang msgcnmultisubgraphbasedheterogeneousgraphconvolutionnetworkembedding AT jianpeng msgcnmultisubgraphbasedheterogeneousgraphconvolutionnetworkembedding
_version_	1718437895444889600

MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding

Ejemplares similares