Attribute-Aware Graph Aggregation for Sequential Recommendation
In this paper, we address the challenge of dynamic evolution of user preferences and propose an attribute-sequence-based recommendation model to improve the accuracy and interpretability of recommendation systems. Traditional approaches usually rely on item sequences to model user behavior, but igno...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/9/1386 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850278768035233792 |
|---|---|
| author | Yiming Qu Yang Fang Zhen Tan Weidong Xiao |
| author_facet | Yiming Qu Yang Fang Zhen Tan Weidong Xiao |
| author_sort | Yiming Qu |
| collection | DOAJ |
| description | In this paper, we address the challenge of dynamic evolution of user preferences and propose an attribute-sequence-based recommendation model to improve the accuracy and interpretability of recommendation systems. Traditional approaches usually rely on item sequences to model user behavior, but ignore the potential value of attributes shared among different items for preference characterization. To this end, this paper innovatively replaces items in user interaction sequences with attributes, constructs attribute sequences to capture fine-grained preference changes, and reinforces the prioritization of current interests by maintaining the latest state of attributes. Meanwhile, the item–attribute relationship is modeled using LightGCN and a variant of GAT, fusing multi-level features using gated attention mechanism, and introducing rotary encoding to enhance the flexibility of sequence modeling. Experiments on four real datasets (Beauty, Video Games, Men, and Fashion) showed that the model in this paper significantly outperformed the benchmark model in both NDCG@10 and Hit Ratio@10 metrics, with a highest improvement of 6.435% and 3.613%, respectively. The ablation experiments further validated the key role of attribute aggregation and sequence modeling in capturing user preference dynamics. This work provides a new concept for recommender systems that balances fine-grained preference evolution with efficient sequence modeling. |
| format | Article |
| id | doaj-art-5067f5e57d914f97a2cc28c43e7f9620 |
| institution | OA Journals |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-5067f5e57d914f97a2cc28c43e7f96202025-08-20T01:49:20ZengMDPI AGMathematics2227-73902025-04-01139138610.3390/math13091386Attribute-Aware Graph Aggregation for Sequential RecommendationYiming Qu0Yang Fang1Zhen Tan2Weidong Xiao3National Key Laboratory of Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaCollege of Systems Engineering, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaIn this paper, we address the challenge of dynamic evolution of user preferences and propose an attribute-sequence-based recommendation model to improve the accuracy and interpretability of recommendation systems. Traditional approaches usually rely on item sequences to model user behavior, but ignore the potential value of attributes shared among different items for preference characterization. To this end, this paper innovatively replaces items in user interaction sequences with attributes, constructs attribute sequences to capture fine-grained preference changes, and reinforces the prioritization of current interests by maintaining the latest state of attributes. Meanwhile, the item–attribute relationship is modeled using LightGCN and a variant of GAT, fusing multi-level features using gated attention mechanism, and introducing rotary encoding to enhance the flexibility of sequence modeling. Experiments on four real datasets (Beauty, Video Games, Men, and Fashion) showed that the model in this paper significantly outperformed the benchmark model in both NDCG@10 and Hit Ratio@10 metrics, with a highest improvement of 6.435% and 3.613%, respectively. The ablation experiments further validated the key role of attribute aggregation and sequence modeling in capturing user preference dynamics. This work provides a new concept for recommender systems that balances fine-grained preference evolution with efficient sequence modeling.https://www.mdpi.com/2227-7390/13/9/1386recommender systemsequential recommendationitem–attribute graph embedding |
| spellingShingle | Yiming Qu Yang Fang Zhen Tan Weidong Xiao Attribute-Aware Graph Aggregation for Sequential Recommendation Mathematics recommender system sequential recommendation item–attribute graph embedding |
| title | Attribute-Aware Graph Aggregation for Sequential Recommendation |
| title_full | Attribute-Aware Graph Aggregation for Sequential Recommendation |
| title_fullStr | Attribute-Aware Graph Aggregation for Sequential Recommendation |
| title_full_unstemmed | Attribute-Aware Graph Aggregation for Sequential Recommendation |
| title_short | Attribute-Aware Graph Aggregation for Sequential Recommendation |
| title_sort | attribute aware graph aggregation for sequential recommendation |
| topic | recommender system sequential recommendation item–attribute graph embedding |
| url | https://www.mdpi.com/2227-7390/13/9/1386 |
| work_keys_str_mv | AT yimingqu attributeawaregraphaggregationforsequentialrecommendation AT yangfang attributeawaregraphaggregationforsequentialrecommendation AT zhentan attributeawaregraphaggregationforsequentialrecommendation AT weidongxiao attributeawaregraphaggregationforsequentialrecommendation |