Matrix Factorization Recommendation Algorithm Based on Attention Interaction
Recommender systems are widely used in e-commerce, movies, music, social media, and other fields because of their personalized recommendation functions. The recommendation algorithm is used to capture user preferences, item characteristics, and the items that users are interested in are recommended...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/16/3/267 |
| _version_ | 1797239247703375872 |
|---|---|
| author | Chengzhi Mao Zhifeng Wu Yingjie Liu Zhiwei Shi |
| author_facet | Chengzhi Mao Zhifeng Wu Yingjie Liu Zhiwei Shi |
| author_sort | Chengzhi Mao |
| collection | DOAJ |
| description | Recommender systems are widely used in e-commerce, movies, music, social media, and other fields because of their personalized recommendation functions. The recommendation algorithm is used to capture user preferences, item characteristics, and the items that users are interested in are recommended to users. Matrix factorization is widely used in collaborative filtering algorithms because of its simplicity and efficiency. However, the simple dot-product method cannot establish a nonlinear relationship between user latent features and item latent features or make full use of their personalized information. The model of a neural network combined with an attention mechanism can effectively establish a nonlinear relationship between the potential features of users and items and improve the recommendation accuracy of the model. However, it is difficult for the general attention mechanism algorithm to solve the problem of attention interaction when the number of features between the users and items is not the same. To solve the above problems, this paper proposes an attention interaction matrix factorization (AIMF) model. The AIMF model adopts a symmetric structure using MLP calculation. This structure can simultaneously extract the nonlinear features of user latent features and item latent features, thus reducing the computation time of the model. In addition, an improved attention algorithm named slide-attention is included in the model. The algorithm uses the sliding query method to obtain the user’s attention to the latent features of the item and solves the interaction problem among different dimensions of the user, and the latent features of the item. |
| first_indexed | 2024-04-24T17:48:30Z |
| format | Article |
| id | doaj.art-8ec0299e10694239913ee642112c2248 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-24T17:48:30Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-8ec0299e10694239913ee642112c22482024-03-27T14:05:20ZengMDPI AGSymmetry2073-89942024-02-0116326710.3390/sym16030267Matrix Factorization Recommendation Algorithm Based on Attention InteractionChengzhi Mao0Zhifeng Wu1Yingjie Liu2Zhiwei Shi3School of Information Technology Engineering, Tianjin University of Technology and Education, Hexi District, Tianjin 300222, ChinaSchool of Information Technology Engineering, Tianjin University of Technology and Education, Hexi District, Tianjin 300222, ChinaSchool of Information Technology Engineering, Tianjin University of Technology and Education, Hexi District, Tianjin 300222, ChinaSchool of Computer Science, Shaanxi Normal University, 620 West Chang’an Street, Xi’an 710119, China Recommender systems are widely used in e-commerce, movies, music, social media, and other fields because of their personalized recommendation functions. The recommendation algorithm is used to capture user preferences, item characteristics, and the items that users are interested in are recommended to users. Matrix factorization is widely used in collaborative filtering algorithms because of its simplicity and efficiency. However, the simple dot-product method cannot establish a nonlinear relationship between user latent features and item latent features or make full use of their personalized information. The model of a neural network combined with an attention mechanism can effectively establish a nonlinear relationship between the potential features of users and items and improve the recommendation accuracy of the model. However, it is difficult for the general attention mechanism algorithm to solve the problem of attention interaction when the number of features between the users and items is not the same. To solve the above problems, this paper proposes an attention interaction matrix factorization (AIMF) model. The AIMF model adopts a symmetric structure using MLP calculation. This structure can simultaneously extract the nonlinear features of user latent features and item latent features, thus reducing the computation time of the model. In addition, an improved attention algorithm named slide-attention is included in the model. The algorithm uses the sliding query method to obtain the user’s attention to the latent features of the item and solves the interaction problem among different dimensions of the user, and the latent features of the item.https://www.mdpi.com/2073-8994/16/3/267artificial intelligencerecommender systemcollaborative filteringslide attentionattention mechanism |
| spellingShingle | Chengzhi Mao Zhifeng Wu Yingjie Liu Zhiwei Shi Matrix Factorization Recommendation Algorithm Based on Attention Interaction Symmetry artificial intelligence recommender system collaborative filtering slide attention attention mechanism |
| title | Matrix Factorization Recommendation Algorithm Based on Attention Interaction |
| title_full | Matrix Factorization Recommendation Algorithm Based on Attention Interaction |
| title_fullStr | Matrix Factorization Recommendation Algorithm Based on Attention Interaction |
| title_full_unstemmed | Matrix Factorization Recommendation Algorithm Based on Attention Interaction |
| title_short | Matrix Factorization Recommendation Algorithm Based on Attention Interaction |
| title_sort | matrix factorization recommendation algorithm based on attention interaction |
| topic | artificial intelligence recommender system collaborative filtering slide attention attention mechanism |
| url | https://www.mdpi.com/2073-8994/16/3/267 |
| work_keys_str_mv | AT chengzhimao matrixfactorizationrecommendationalgorithmbasedonattentioninteraction AT zhifengwu matrixfactorizationrecommendationalgorithmbasedonattentioninteraction AT yingjieliu matrixfactorizationrecommendationalgorithmbasedonattentioninteraction AT zhiweishi matrixfactorizationrecommendationalgorithmbasedonattentioninteraction |