A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations

In recent years, many researchers have devoted time to designing algorithms used to introduce external information from knowledge graphs, to solve the problems of data sparseness and the cold start, and thus improve the performance of recommendation systems. Inspired by these studies, we proposed KA...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Dehai Zhang, Xiaobo Yang, Linan Liu, Qing Liu
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/5542755bebeb416782e63d307c64ac60
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5542755bebeb416782e63d307c64ac60
record_format dspace
spelling oai:doaj.org-article:5542755bebeb416782e63d307c64ac602021-11-11T15:24:11ZA Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations10.3390/app1121104322076-3417https://doaj.org/article/5542755bebeb416782e63d307c64ac602021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10432https://doaj.org/toc/2076-3417In recent years, many researchers have devoted time to designing algorithms used to introduce external information from knowledge graphs, to solve the problems of data sparseness and the cold start, and thus improve the performance of recommendation systems. Inspired by these studies, we proposed KANR, a knowledge graph-enhanced attention aggregation network for making recommendations. This is an end-to-end deep learning model using knowledge graph embedding to enhance the attention aggregation network for making recommendations. It consists of three main parts. The first is the attention aggregation network, which collect the user’s interaction history and captures the user’s preference for each item. The second is the knowledge graph-embedded model, which aims to integrate the knowledge. The semantic information of the nodes and edges in the graph is mapped to the low-dimensional vector space. The final part is the information interaction unit, which is used for fusing the features of two vectors. Experiments showed that our model achieved a stable improvement compared to the baseline model in making recommendations for movies, books, and music.Dehai ZhangXiaobo YangLinan LiuQing LiuMDPI AGarticleknowledge graphpersonalized recommendationattention aggregationTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10432, p 10432 (2021)
institution DOAJ
collection DOAJ
language EN
topic knowledge graph
personalized recommendation
attention aggregation
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle knowledge graph
personalized recommendation
attention aggregation
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Dehai Zhang
Xiaobo Yang
Linan Liu
Qing Liu
A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations
description In recent years, many researchers have devoted time to designing algorithms used to introduce external information from knowledge graphs, to solve the problems of data sparseness and the cold start, and thus improve the performance of recommendation systems. Inspired by these studies, we proposed KANR, a knowledge graph-enhanced attention aggregation network for making recommendations. This is an end-to-end deep learning model using knowledge graph embedding to enhance the attention aggregation network for making recommendations. It consists of three main parts. The first is the attention aggregation network, which collect the user’s interaction history and captures the user’s preference for each item. The second is the knowledge graph-embedded model, which aims to integrate the knowledge. The semantic information of the nodes and edges in the graph is mapped to the low-dimensional vector space. The final part is the information interaction unit, which is used for fusing the features of two vectors. Experiments showed that our model achieved a stable improvement compared to the baseline model in making recommendations for movies, books, and music.
format article
author Dehai Zhang
Xiaobo Yang
Linan Liu
Qing Liu
author_facet Dehai Zhang
Xiaobo Yang
Linan Liu
Qing Liu
author_sort Dehai Zhang
title A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations
title_short A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations
title_full A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations
title_fullStr A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations
title_full_unstemmed A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations
title_sort knowledge graph-enhanced attention aggregation network for making recommendations
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/5542755bebeb416782e63d307c64ac60
work_keys_str_mv AT dehaizhang aknowledgegraphenhancedattentionaggregationnetworkformakingrecommendations
AT xiaoboyang aknowledgegraphenhancedattentionaggregationnetworkformakingrecommendations
AT linanliu aknowledgegraphenhancedattentionaggregationnetworkformakingrecommendations
AT qingliu aknowledgegraphenhancedattentionaggregationnetworkformakingrecommendations
AT dehaizhang knowledgegraphenhancedattentionaggregationnetworkformakingrecommendations
AT xiaoboyang knowledgegraphenhancedattentionaggregationnetworkformakingrecommendations
AT linanliu knowledgegraphenhancedattentionaggregationnetworkformakingrecommendations
AT qingliu knowledgegraphenhancedattentionaggregationnetworkformakingrecommendations
_version_ 1718435366144311296