Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding

Wang, Shuli; Li, Xuewen; Kou, Xiaomeng; Zhang, Jin; Zheng, Shaojie; Wang, Jinlong; Gong, Jibing

doi:10.3390/a14090263

Open AccessArticle

Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding

by

Shuli Wang

¹

,

Xuewen Li

²

,

Xiaomeng Kou

²

,

Jin Zhang

^2,†

,

Shaojie Zheng

^2,†

,

Jinlong Wang

²

and

Jibing Gong

^2,3,4,*

¹

School of Science, Yanshan University, Qinhuangdao 066004, China

²

School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China

³

The Key Lab for Computer Virtual Technology and System Integration of Hebei Province, Yanshan University, Qinhuangdao 066004, China

⁴

Key Laboratory for Software Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, China

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Algorithms 2021, 14(9), 263; https://doi.org/10.3390/a14090263

Submission received: 8 August 2021 / Revised: 27 August 2021 / Accepted: 30 August 2021 / Published: 31 August 2021

(This article belongs to the Special Issue Algorithms for Sequential Analysis)

Download

Browse Figures

Review Reports Versions Notes

Abstract

Predicting users’ next behavior through learning users’ preferences according to the users’ historical behaviors is known as sequential recommendation. In this task, learning sequence representation by modeling the pairwise relationship between items in the sequence to capture their long-range dependencies is crucial. In this paper, we propose a novel deep neural network named graph convolutional network transformer recommender (GCNTRec). GCNTRec is capable of learning effective item representation in a user’s historical behaviors sequence, which involves extracting the correlation between the target node and multi-layer neighbor nodes on the graphs constructed under the heterogeneous information networks in an end-to-end fashion through a graph convolutional network (GCN) with degree encoding, while the capturing long-range dependencies of items in a sequence through the transformer encoder model. Using this multi-dimensional vector representation, items related to a user historical behavior sequence can be easily predicted. We empirically evaluated GCNTRec on multiple public datasets. The experimental results show that our approach can effectively predict subsequent relevant items and outperforms previous techniques.

Keywords: sequential recommendation; graph neural networks; transformer encoder; degree encoding

Share and Cite

MDPI and ACS Style

Wang, S.; Li, X.; Kou, X.; Zhang, J.; Zheng, S.; Wang, J.; Gong, J. Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding. Algorithms 2021, 14, 263. https://doi.org/10.3390/a14090263

AMA Style

Wang S, Li X, Kou X, Zhang J, Zheng S, Wang J, Gong J. Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding. Algorithms. 2021; 14(9):263. https://doi.org/10.3390/a14090263

Chicago/Turabian Style

Wang, Shuli, Xuewen Li, Xiaomeng Kou, Jin Zhang, Shaojie Zheng, Jinlong Wang, and Jibing Gong. 2021. "Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding" Algorithms 14, no. 9: 263. https://doi.org/10.3390/a14090263

APA Style

Wang, S., Li, X., Kou, X., Zhang, J., Zheng, S., Wang, J., & Gong, J. (2021). Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding. Algorithms, 14(9), 263. https://doi.org/10.3390/a14090263

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Sequential Recommendation through Graph Neural Networks and Transformer Encoder with Degree Encoding

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI