Search-based Time-aware Graph-enhanced Recommendation with Sequential Behavior Data
ACM Transactions on Recommender Systems · 31.12.2024 · 2 (4) · 1-29
DOI: 10.1145/3605356 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Recommender Systems, online erschienen am 31.07.2024. Verfasst von Lei Zheng und 8 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: China Merchants Bank Credit Card Center, The Shanghai Jiao Tong University Team, Shanghai Municipal Science and Technology Major Project.
Abstract (Originalsprache)
Extending from sequential recommendation models, in this article, we present a novel framework named Search-based Time-Aware Recommendation (STARec), which first retrieves the historical behaviors of the given user through a search-based retriever and then captures the user’s evolving demands over time through a time-aware sequential network. We notice that the key insight of STARec is to use the feature and labels to augment the representations, and thus the effectiveness of STARec relies on the acquisition of rich browsing records of the target user and powerful representation of each browsed item and thus its performance could heavily drop regarding long-tail users and items. To this end, we extend STARec by constructing a graph upon the user–item interactions and leveraging the graph structure to enhance the representation learning. We call this extended version Search-based Time-Aware Graph-Enhanced Recommendation (STAGE). We conduct extensive experiments on three real-world datasets and STARec achieves consistent superiority. We further compare STAGE against STARec long-tail users and our results demonstrate that STAGE could outperform STARec at most cases. Results of online A/B tests show that STARec and STAGE achieve an average click-through rate improvement of around 6% and 1.5% in the two main item recommendation scenarios, respectively. 1
Förderung
- China Merchants Bank Credit Card Center
- The Shanghai Jiao Tong University Team
- Shanghai Municipal Science and Technology Major Project
- National Natural Science Foundation of China
Zitieren
APA
Zheng, L., Chai, H., Chen, X., Jin, J., Zhang, W., Yu, Y., Guo, X., Ge, C., & Feng, Z. (2024). Search-based Time-aware Graph-enhanced Recommendation with Sequential Behavior Data. ACM Transactions on Recommender Systems, 2(4), 1-29. https://doi.org/10.1145/3605356
Vancouver
Zheng L, Chai H, Chen X, Jin J, Zhang W, Yu Y, et al. Search-based Time-aware Graph-enhanced Recommendation with Sequential Behavior Data. ACM Transactions on Recommender Systems. 2024;2(4):1-29. doi:10.1145/3605356
BibTeX
@article{Zheng2024,
author = {Zheng, Lei and Chai, Huacan and Chen, Xianyu and Jin, Jiarui and Zhang, Weinan and Yu, Yong and Guo, Xiaodong and Ge, Can and Feng, Ziming},
title = {Search-based Time-aware Graph-enhanced Recommendation with Sequential Behavior Data},
journal = {ACM Transactions on Recommender Systems},
year = {2024},
volume = {2},
number = {4},
pages = {1--29},
doi = {10.1145/3605356}
}
EUVIMED