Personal Interest Attention Graph Neural Networks for Session-Based Recommendation

Session-based recommendations aim to predict a user’s next click based on the user’s current and historical sessions, which can be applied to shopping websites and APPs. Existing session-based recommendation methods cannot accurately capture the complex transitions between items. In addition, some a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiangde Zhang, Yuan Zhou, Jianping Wang, Xiaojun Lu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	session-based recommendation graph neural networks attention recommendation system Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/9d9eb41812454a14a74fee1a87a7c478
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9d9eb41812454a14a74fee1a87a7c478
record_format	dspace
spelling	oai:doaj.org-article:9d9eb41812454a14a74fee1a87a7c4782021-11-25T17:30:13ZPersonal Interest Attention Graph Neural Networks for Session-Based Recommendation10.3390/e231115001099-4300https://doaj.org/article/9d9eb41812454a14a74fee1a87a7c4782021-11-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1500https://doaj.org/toc/1099-4300Session-based recommendations aim to predict a user’s next click based on the user’s current and historical sessions, which can be applied to shopping websites and APPs. Existing session-based recommendation methods cannot accurately capture the complex transitions between items. In addition, some approaches compress sessions into a fixed representation vector without taking into account the user’s interest preferences at the current moment, thus limiting the accuracy of recommendations. Considering the diversity of items and users’ interests, a personalized interest attention graph neural network (PIA-GNN) is proposed for session-based recommendation. This approach utilizes personalized graph convolutional networks (PGNN) to capture complex transitions between items, invoking an interest-aware mechanism to activate users’ interest in different items adaptively. In addition, a self-attention layer is used to capture long-term dependencies between items when capturing users’ long-term preferences. In this paper, the cross-entropy loss is used as the objective function to train our model. We conduct rich experiments on two real datasets, and the results show that PIA-GNN outperforms existing personalized session-aware recommendation methods.Xiangde ZhangYuan ZhouJianping WangXiaojun LuMDPI AGarticlesession-based recommendationgraph neural networksattentionrecommendation systemScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1500, p 1500 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	session-based recommendation graph neural networks attention recommendation system Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	session-based recommendation graph neural networks attention recommendation system Science Q Astrophysics QB460-466 Physics QC1-999 Xiangde Zhang Yuan Zhou Jianping Wang Xiaojun Lu Personal Interest Attention Graph Neural Networks for Session-Based Recommendation
description	Session-based recommendations aim to predict a user’s next click based on the user’s current and historical sessions, which can be applied to shopping websites and APPs. Existing session-based recommendation methods cannot accurately capture the complex transitions between items. In addition, some approaches compress sessions into a fixed representation vector without taking into account the user’s interest preferences at the current moment, thus limiting the accuracy of recommendations. Considering the diversity of items and users’ interests, a personalized interest attention graph neural network (PIA-GNN) is proposed for session-based recommendation. This approach utilizes personalized graph convolutional networks (PGNN) to capture complex transitions between items, invoking an interest-aware mechanism to activate users’ interest in different items adaptively. In addition, a self-attention layer is used to capture long-term dependencies between items when capturing users’ long-term preferences. In this paper, the cross-entropy loss is used as the objective function to train our model. We conduct rich experiments on two real datasets, and the results show that PIA-GNN outperforms existing personalized session-aware recommendation methods.
format	article
author	Xiangde Zhang Yuan Zhou Jianping Wang Xiaojun Lu
author_facet	Xiangde Zhang Yuan Zhou Jianping Wang Xiaojun Lu
author_sort	Xiangde Zhang
title	Personal Interest Attention Graph Neural Networks for Session-Based Recommendation
title_short	Personal Interest Attention Graph Neural Networks for Session-Based Recommendation
title_full	Personal Interest Attention Graph Neural Networks for Session-Based Recommendation
title_fullStr	Personal Interest Attention Graph Neural Networks for Session-Based Recommendation
title_full_unstemmed	Personal Interest Attention Graph Neural Networks for Session-Based Recommendation
title_sort	personal interest attention graph neural networks for session-based recommendation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9d9eb41812454a14a74fee1a87a7c478
work_keys_str_mv	AT xiangdezhang personalinterestattentiongraphneuralnetworksforsessionbasedrecommendation AT yuanzhou personalinterestattentiongraphneuralnetworksforsessionbasedrecommendation AT jianpingwang personalinterestattentiongraphneuralnetworksforsessionbasedrecommendation AT xiaojunlu personalinterestattentiongraphneuralnetworksforsessionbasedrecommendation
_version_	1718412301236699136

Personal Interest Attention Graph Neural Networks for Session-Based Recommendation

Ejemplares similares