A Recommendation Algorithm Combining Local and Global Interest Features
Due to the ability of knowledge graph to effectively solve the sparsity problem of collaborative filtering, knowledge graph (KG) has been widely studied and applied as auxiliary information in the field of recommendation systems. However, existing KG-based recommendation methods mainly focus on lear...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/8/1857 |
| _version_ | 1797605651759759360 |
|---|---|
| author | Xiaoyuan Song Jiwei Qin Qiulin Ren |
| author_facet | Xiaoyuan Song Jiwei Qin Qiulin Ren |
| author_sort | Xiaoyuan Song |
| collection | DOAJ |
| description | Due to the ability of knowledge graph to effectively solve the sparsity problem of collaborative filtering, knowledge graph (KG) has been widely studied and applied as auxiliary information in the field of recommendation systems. However, existing KG-based recommendation methods mainly focus on learning its representation from the neighborhood of target items, ignoring the influence of other items on the target item. The learning focuses on the local feature representation of the target item, which is not sufficient to effectively explore the user’s preference degree for the target item. To address the above issues, in this paper, an approach combining users’ local interest features with global interest features (KGG) is proposed to efficiently explore the user’s preference level for the target item, which learns the user’s local interest features and global interest features for target item through Knowledge Graph Convolutional Network and Generative Adversarial Network (GAN). Specifically, this paper first utilizes the Knowledge Graph Convolutional Network to mine related attributes on the knowledge graph to effectively capture item correlations and obtain the local feature representation of the target item, then uses the matrix factorization method to learn the user’s local interest features for target items. Secondly, it uses GAN to learn the user’s global interest features for target items from the implicit interaction matrix. Finally, a linear fusion layer is designed to effectively fuse the user’s local and global interests towards target items to obtain the final click prediction. Experimental results on three real datasets show that the proposed method not only effectively integrates the user’s local and global interests but also further alleviates the problem of data sparsity. Compared with the current baselines for knowledge graph-based systems, the KGG method achieves a maximum improvement of 8.1% and 7.6% in AUC and ACC, respectively. |
| first_indexed | 2024-03-11T05:04:07Z |
| format | Article |
| id | doaj.art-82ed33e8edc841f1a7d8d880f9dbca79 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T05:04:07Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-82ed33e8edc841f1a7d8d880f9dbca792023-11-17T19:01:52ZengMDPI AGElectronics2079-92922023-04-01128185710.3390/electronics12081857A Recommendation Algorithm Combining Local and Global Interest FeaturesXiaoyuan Song0Jiwei Qin1Qiulin Ren2School of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaSchool of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaSchool of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaDue to the ability of knowledge graph to effectively solve the sparsity problem of collaborative filtering, knowledge graph (KG) has been widely studied and applied as auxiliary information in the field of recommendation systems. However, existing KG-based recommendation methods mainly focus on learning its representation from the neighborhood of target items, ignoring the influence of other items on the target item. The learning focuses on the local feature representation of the target item, which is not sufficient to effectively explore the user’s preference degree for the target item. To address the above issues, in this paper, an approach combining users’ local interest features with global interest features (KGG) is proposed to efficiently explore the user’s preference level for the target item, which learns the user’s local interest features and global interest features for target item through Knowledge Graph Convolutional Network and Generative Adversarial Network (GAN). Specifically, this paper first utilizes the Knowledge Graph Convolutional Network to mine related attributes on the knowledge graph to effectively capture item correlations and obtain the local feature representation of the target item, then uses the matrix factorization method to learn the user’s local interest features for target items. Secondly, it uses GAN to learn the user’s global interest features for target items from the implicit interaction matrix. Finally, a linear fusion layer is designed to effectively fuse the user’s local and global interests towards target items to obtain the final click prediction. Experimental results on three real datasets show that the proposed method not only effectively integrates the user’s local and global interests but also further alleviates the problem of data sparsity. Compared with the current baselines for knowledge graph-based systems, the KGG method achieves a maximum improvement of 8.1% and 7.6% in AUC and ACC, respectively.https://www.mdpi.com/2079-9292/12/8/1857recommendation systemknowledge graphKnowledge Graph Convolutional NetworkGenerative Adversarial Networkinterest features |
| spellingShingle | Xiaoyuan Song Jiwei Qin Qiulin Ren A Recommendation Algorithm Combining Local and Global Interest Features Electronics recommendation system knowledge graph Knowledge Graph Convolutional Network Generative Adversarial Network interest features |
| title | A Recommendation Algorithm Combining Local and Global Interest Features |
| title_full | A Recommendation Algorithm Combining Local and Global Interest Features |
| title_fullStr | A Recommendation Algorithm Combining Local and Global Interest Features |
| title_full_unstemmed | A Recommendation Algorithm Combining Local and Global Interest Features |
| title_short | A Recommendation Algorithm Combining Local and Global Interest Features |
| title_sort | recommendation algorithm combining local and global interest features |
| topic | recommendation system knowledge graph Knowledge Graph Convolutional Network Generative Adversarial Network interest features |
| url | https://www.mdpi.com/2079-9292/12/8/1857 |
| work_keys_str_mv | AT xiaoyuansong arecommendationalgorithmcombininglocalandglobalinterestfeatures AT jiweiqin arecommendationalgorithmcombininglocalandglobalinterestfeatures AT qiulinren arecommendationalgorithmcombininglocalandglobalinterestfeatures AT xiaoyuansong recommendationalgorithmcombininglocalandglobalinterestfeatures AT jiweiqin recommendationalgorithmcombininglocalandglobalinterestfeatures AT qiulinren recommendationalgorithmcombininglocalandglobalinterestfeatures |