GSRec: A Graph-Sequence Recommendation System Based on Reverse-Order Graph and User Embedding
At present, sequence-based models have various applications in recommendation systems; these models recommend the interested items of the user according to the user’s behavioral sequence. However, sequence-based models have a limitation of length. When the length of the user’s behavioral sequence ex...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/1/164 |
| _version_ | 1797358438147162112 |
|---|---|
| author | Xulin Ma Jiajia Tan Linan Zhu Xiaoran Yan Xiangjie Kong |
| author_facet | Xulin Ma Jiajia Tan Linan Zhu Xiaoran Yan Xiangjie Kong |
| author_sort | Xulin Ma |
| collection | DOAJ |
| description | At present, sequence-based models have various applications in recommendation systems; these models recommend the interested items of the user according to the user’s behavioral sequence. However, sequence-based models have a limitation of length. When the length of the user’s behavioral sequence exceeds the limitation of the model, the model cannot take advantage of the complete behavioral sequence of the user and cannot know the user’s holistic interests. The accuracy of the model then goes down. Meanwhile, sequence-based models only pay attention to the sequential signals of the data but do not pay attention to the spatial signals of the data, which will also affect the model’s accuracy. This paper proposes a graph sequence-based model called GSRec that combines Graph Convolutional Network (GCN) and Transformer to solve these problems. In the GCN part we designed a reverse-order graph, and in the Transformer part we introduced the user embedding. The reverse-order graph and the user embedding can make the combination of GCN and Transformer more efficient. Experiments on six datasets show that GSRec outperforms the current state-of-the-art (SOTA) models. |
| first_indexed | 2024-03-08T15:01:01Z |
| format | Article |
| id | doaj.art-09436a0ea43a43b3ae7727143ebfb230 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-08T15:01:01Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-09436a0ea43a43b3ae7727143ebfb2302024-01-10T15:03:48ZengMDPI AGMathematics2227-73902024-01-0112116410.3390/math12010164GSRec: A Graph-Sequence Recommendation System Based on Reverse-Order Graph and User EmbeddingXulin Ma0Jiajia Tan1Linan Zhu2Xiaoran Yan3Xiangjie Kong4College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaResearch Institute of Artificial Intelligence, Zhejiang Lab, Hangzhou 310023, ChinaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaAt present, sequence-based models have various applications in recommendation systems; these models recommend the interested items of the user according to the user’s behavioral sequence. However, sequence-based models have a limitation of length. When the length of the user’s behavioral sequence exceeds the limitation of the model, the model cannot take advantage of the complete behavioral sequence of the user and cannot know the user’s holistic interests. The accuracy of the model then goes down. Meanwhile, sequence-based models only pay attention to the sequential signals of the data but do not pay attention to the spatial signals of the data, which will also affect the model’s accuracy. This paper proposes a graph sequence-based model called GSRec that combines Graph Convolutional Network (GCN) and Transformer to solve these problems. In the GCN part we designed a reverse-order graph, and in the Transformer part we introduced the user embedding. The reverse-order graph and the user embedding can make the combination of GCN and Transformer more efficient. Experiments on six datasets show that GSRec outperforms the current state-of-the-art (SOTA) models.https://www.mdpi.com/2227-7390/12/1/164graph neural networksequential recommendationrepresentation learning |
| spellingShingle | Xulin Ma Jiajia Tan Linan Zhu Xiaoran Yan Xiangjie Kong GSRec: A Graph-Sequence Recommendation System Based on Reverse-Order Graph and User Embedding Mathematics graph neural network sequential recommendation representation learning |
| title | GSRec: A Graph-Sequence Recommendation System Based on Reverse-Order Graph and User Embedding |
| title_full | GSRec: A Graph-Sequence Recommendation System Based on Reverse-Order Graph and User Embedding |
| title_fullStr | GSRec: A Graph-Sequence Recommendation System Based on Reverse-Order Graph and User Embedding |
| title_full_unstemmed | GSRec: A Graph-Sequence Recommendation System Based on Reverse-Order Graph and User Embedding |
| title_short | GSRec: A Graph-Sequence Recommendation System Based on Reverse-Order Graph and User Embedding |
| title_sort | gsrec a graph sequence recommendation system based on reverse order graph and user embedding |
| topic | graph neural network sequential recommendation representation learning |
| url | https://www.mdpi.com/2227-7390/12/1/164 |
| work_keys_str_mv | AT xulinma gsrecagraphsequencerecommendationsystembasedonreverseordergraphanduserembedding AT jiajiatan gsrecagraphsequencerecommendationsystembasedonreverseordergraphanduserembedding AT linanzhu gsrecagraphsequencerecommendationsystembasedonreverseordergraphanduserembedding AT xiaoranyan gsrecagraphsequencerecommendationsystembasedonreverseordergraphanduserembedding AT xiangjiekong gsrecagraphsequencerecommendationsystembasedonreverseordergraphanduserembedding |