Improved Metric-Based Recommender by Historical Interactions
A remarkable success in recommendations has been achieved by using methods based on metric learning, especially in digital marketing. However, the existing methods do not consider the relative preferences among items that users like. To overcome this issue, we propose an improved recommender model....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8822676/ |
| _version_ | 1798002015879561216 |
|---|---|
| author | Yubo Jiang Yunfang Zhu Xin Du Tao Jin |
| author_facet | Yubo Jiang Yunfang Zhu Xin Du Tao Jin |
| author_sort | Yubo Jiang |
| collection | DOAJ |
| description | A remarkable success in recommendations has been achieved by using methods based on metric learning, especially in digital marketing. However, the existing methods do not consider the relative preferences among items that users like. To overcome this issue, we propose an improved recommender model. First, the model analyses the user-item bipartite graph from historical interactions, and collects user-item similarities based on the topological features from this graph. Then, similar to other metric-based methods, both users and items are embedded as latent positions in a low-dimensional space, where users’ preferences on items are modelled as distances. Thus, we propose an improved metric-based recommender, i.e. the Graph Embedded Metric Factorisation recommender, under the assumptions that (1) the distance between a target user and an interacted-with item is determined by their topological similarity, and (2) for a target user, non-interacted items are located farther away than interacted-with ones. Comprehensive experiments on three practical datasets were implemented. Empirical results indicate that our improved recommender outperforms current state-of-the-art methods when making personalised recommendations based on users’ implicit feedback. |
| first_indexed | 2024-04-11T11:45:30Z |
| format | Article |
| id | doaj.art-784d4f3fe2ce44e3b949cc49805f53ea |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T11:45:30Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-784d4f3fe2ce44e3b949cc49805f53ea2022-12-22T04:25:35ZengIEEEIEEE Access2169-35362019-01-01712596912597510.1109/ACCESS.2019.29389708822676Improved Metric-Based Recommender by Historical InteractionsYubo Jiang0Yunfang Zhu1Xin Du2https://orcid.org/0000-0002-6215-9733Tao Jin3College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, ChinaCollege of Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou, ChinaCollege of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, ChinaCollege of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, ChinaA remarkable success in recommendations has been achieved by using methods based on metric learning, especially in digital marketing. However, the existing methods do not consider the relative preferences among items that users like. To overcome this issue, we propose an improved recommender model. First, the model analyses the user-item bipartite graph from historical interactions, and collects user-item similarities based on the topological features from this graph. Then, similar to other metric-based methods, both users and items are embedded as latent positions in a low-dimensional space, where users’ preferences on items are modelled as distances. Thus, we propose an improved metric-based recommender, i.e. the Graph Embedded Metric Factorisation recommender, under the assumptions that (1) the distance between a target user and an interacted-with item is determined by their topological similarity, and (2) for a target user, non-interacted items are located farther away than interacted-with ones. Comprehensive experiments on three practical datasets were implemented. Empirical results indicate that our improved recommender outperforms current state-of-the-art methods when making personalised recommendations based on users’ implicit feedback.https://ieeexplore.ieee.org/document/8822676/Implicit feedbacklatent positionsmetric learningpoint-wise similarity and pair-wise rankingpersonalised recommendation |
| spellingShingle | Yubo Jiang Yunfang Zhu Xin Du Tao Jin Improved Metric-Based Recommender by Historical Interactions IEEE Access Implicit feedback latent positions metric learning point-wise similarity and pair-wise ranking personalised recommendation |
| title | Improved Metric-Based Recommender by Historical Interactions |
| title_full | Improved Metric-Based Recommender by Historical Interactions |
| title_fullStr | Improved Metric-Based Recommender by Historical Interactions |
| title_full_unstemmed | Improved Metric-Based Recommender by Historical Interactions |
| title_short | Improved Metric-Based Recommender by Historical Interactions |
| title_sort | improved metric based recommender by historical interactions |
| topic | Implicit feedback latent positions metric learning point-wise similarity and pair-wise ranking personalised recommendation |
| url | https://ieeexplore.ieee.org/document/8822676/ |
| work_keys_str_mv | AT yubojiang improvedmetricbasedrecommenderbyhistoricalinteractions AT yunfangzhu improvedmetricbasedrecommenderbyhistoricalinteractions AT xindu improvedmetricbasedrecommenderbyhistoricalinteractions AT taojin improvedmetricbasedrecommenderbyhistoricalinteractions |