The Graph Attention Recommendation Method for Enhancing User Features Based on Knowledge Graphs
Knowledge graphs have shown great potential in alleviating the data sparsity problem in recommendation systems. However, existing graph-attention-based recommendation methods primarily focus on user–item–entity interactions, overlooking potential relationships between users while introducing noisy e...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/3/390 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849717672380465152 |
|---|---|
| author | Hui Wang Qin Li Huilan Luo Yanfei Tang |
| author_facet | Hui Wang Qin Li Huilan Luo Yanfei Tang |
| author_sort | Hui Wang |
| collection | DOAJ |
| description | Knowledge graphs have shown great potential in alleviating the data sparsity problem in recommendation systems. However, existing graph-attention-based recommendation methods primarily focus on user–item–entity interactions, overlooking potential relationships between users while introducing noisy entities and redundant high-order information. To address these challenges, this paper proposes a graph-attention-based recommendation method that enhances user features using knowledge graphs (KGAEUF). This method models user relationships through collaborative propagation, links entities via similar user entities, and filters highly relevant entities from both user–entity and user–relation perspectives to reduce noise interference. In multi-layer propagation, a distance-aware weight allocation mechanism is introduced to optimize high-order information aggregation. Experimental results demonstrate that KGAEUF outperforms existing methods on AUC and F1 metrics on the Last.FM and Book-Crossing datasets, validating the model’s effectiveness. |
| format | Article |
| id | doaj-art-ef5a6c786f8044b3aa291326e59f1e3f |
| institution | DOAJ |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-ef5a6c786f8044b3aa291326e59f1e3f2025-08-20T03:12:35ZengMDPI AGMathematics2227-73902025-01-0113339010.3390/math13030390The Graph Attention Recommendation Method for Enhancing User Features Based on Knowledge GraphsHui Wang0Qin Li1Huilan Luo2Yanfei Tang3School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaSchool of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaSchool of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaSchool of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaKnowledge graphs have shown great potential in alleviating the data sparsity problem in recommendation systems. However, existing graph-attention-based recommendation methods primarily focus on user–item–entity interactions, overlooking potential relationships between users while introducing noisy entities and redundant high-order information. To address these challenges, this paper proposes a graph-attention-based recommendation method that enhances user features using knowledge graphs (KGAEUF). This method models user relationships through collaborative propagation, links entities via similar user entities, and filters highly relevant entities from both user–entity and user–relation perspectives to reduce noise interference. In multi-layer propagation, a distance-aware weight allocation mechanism is introduced to optimize high-order information aggregation. Experimental results demonstrate that KGAEUF outperforms existing methods on AUC and F1 metrics on the Last.FM and Book-Crossing datasets, validating the model’s effectiveness.https://www.mdpi.com/2227-7390/13/3/390recommendation systemgraph neural networkknowledge graphgraph attention networkbinary classification recommendation |
| spellingShingle | Hui Wang Qin Li Huilan Luo Yanfei Tang The Graph Attention Recommendation Method for Enhancing User Features Based on Knowledge Graphs Mathematics recommendation system graph neural network knowledge graph graph attention network binary classification recommendation |
| title | The Graph Attention Recommendation Method for Enhancing User Features Based on Knowledge Graphs |
| title_full | The Graph Attention Recommendation Method for Enhancing User Features Based on Knowledge Graphs |
| title_fullStr | The Graph Attention Recommendation Method for Enhancing User Features Based on Knowledge Graphs |
| title_full_unstemmed | The Graph Attention Recommendation Method for Enhancing User Features Based on Knowledge Graphs |
| title_short | The Graph Attention Recommendation Method for Enhancing User Features Based on Knowledge Graphs |
| title_sort | graph attention recommendation method for enhancing user features based on knowledge graphs |
| topic | recommendation system graph neural network knowledge graph graph attention network binary classification recommendation |
| url | https://www.mdpi.com/2227-7390/13/3/390 |
| work_keys_str_mv | AT huiwang thegraphattentionrecommendationmethodforenhancinguserfeaturesbasedonknowledgegraphs AT qinli thegraphattentionrecommendationmethodforenhancinguserfeaturesbasedonknowledgegraphs AT huilanluo thegraphattentionrecommendationmethodforenhancinguserfeaturesbasedonknowledgegraphs AT yanfeitang thegraphattentionrecommendationmethodforenhancinguserfeaturesbasedonknowledgegraphs AT huiwang graphattentionrecommendationmethodforenhancinguserfeaturesbasedonknowledgegraphs AT qinli graphattentionrecommendationmethodforenhancinguserfeaturesbasedonknowledgegraphs AT huilanluo graphattentionrecommendationmethodforenhancinguserfeaturesbasedonknowledgegraphs AT yanfeitang graphattentionrecommendationmethodforenhancinguserfeaturesbasedonknowledgegraphs |