A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern

For personalized recommender systems, matrix factorization and its variants have become mainstream in collaborative filtering. However, the dot product in matrix factorization does not satisfy the triangle inequality and therefore fails to capture fine-grained information. Metric learning-based mode...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xin Zhang, Jiwei Qin, Jiong Zheng
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	recommender systems social recommendation metric learning Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/e291a1667f834340a44ae68e6a51c3f6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e291a1667f834340a44ae68e6a51c3f6
record_format	dspace
spelling	oai:doaj.org-article:e291a1667f834340a44ae68e6a51c3f62021-11-25T19:07:13ZA Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern10.3390/sym131121582073-8994https://doaj.org/article/e291a1667f834340a44ae68e6a51c3f62021-11-01T00:00:00Zhttps://www.mdpi.com/2073-8994/13/11/2158https://doaj.org/toc/2073-8994For personalized recommender systems, matrix factorization and its variants have become mainstream in collaborative filtering. However, the dot product in matrix factorization does not satisfy the triangle inequality and therefore fails to capture fine-grained information. Metric learning-based models have been shown to be better at capturing fine-grained information than matrix factorization. Nevertheless, most of these models only focus on rating data and social information, which are not sufficient for dealing with the challenges of data sparsity. In this paper, we propose a metric learning-based social recommendation model called SRMC. SRMC exploits users’ co-occurrence patterns to discover their potentially similar or dissimilar users with symmetric relationships and change their relative positions to achieve better recommendations. Experiments on three public datasets show that our model is more effective than the compared models.Xin ZhangJiwei QinJiong ZhengMDPI AGarticlerecommender systemssocial recommendationmetric learningMathematicsQA1-939ENSymmetry, Vol 13, Iss 2158, p 2158 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	recommender systems social recommendation metric learning Mathematics QA1-939
spellingShingle	recommender systems social recommendation metric learning Mathematics QA1-939 Xin Zhang Jiwei Qin Jiong Zheng A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern
description	For personalized recommender systems, matrix factorization and its variants have become mainstream in collaborative filtering. However, the dot product in matrix factorization does not satisfy the triangle inequality and therefore fails to capture fine-grained information. Metric learning-based models have been shown to be better at capturing fine-grained information than matrix factorization. Nevertheless, most of these models only focus on rating data and social information, which are not sufficient for dealing with the challenges of data sparsity. In this paper, we propose a metric learning-based social recommendation model called SRMC. SRMC exploits users’ co-occurrence patterns to discover their potentially similar or dissimilar users with symmetric relationships and change their relative positions to achieve better recommendations. Experiments on three public datasets show that our model is more effective than the compared models.
format	article
author	Xin Zhang Jiwei Qin Jiong Zheng
author_facet	Xin Zhang Jiwei Qin Jiong Zheng
author_sort	Xin Zhang
title	A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern
title_short	A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern
title_full	A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern
title_fullStr	A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern
title_full_unstemmed	A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern
title_sort	social recommendation based on metric learning and users’ co-occurrence pattern
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/e291a1667f834340a44ae68e6a51c3f6
work_keys_str_mv	AT xinzhang asocialrecommendationbasedonmetriclearninganduserscooccurrencepattern AT jiweiqin asocialrecommendationbasedonmetriclearninganduserscooccurrencepattern AT jiongzheng asocialrecommendationbasedonmetriclearninganduserscooccurrencepattern AT xinzhang socialrecommendationbasedonmetriclearninganduserscooccurrencepattern AT jiweiqin socialrecommendationbasedonmetriclearninganduserscooccurrencepattern AT jiongzheng socialrecommendationbasedonmetriclearninganduserscooccurrencepattern
_version_	1718410311215611904

A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern

Ejemplares similares