EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bayesian attention‐based user behaviour modelling for click‐through rate prediction

Yihao Zhang, Mian Chen, Ruizhen Chen, Chu Zhao, Meng Yuan, Zhu Sun

CAAI Transactions on Intelligence Technology · 2024-10 · 9 (5) · 1320-1330

DOI: 10.1049/cit2.12343 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, 2024-05. Verfasst von Yihao Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Exploiting the hierarchical dependence behind user behaviour is critical for click‐through rate (CRT) prediction in recommender systems. Existing methods apply attention mechanisms to obtain the weights of items; however, the authors argue that deterministic attention mechanisms cannot capture the hierarchical dependence between user behaviours because they treat each user behaviour as an independent individual and cannot accurately express users' flexible and changeable interests. To tackle this issue, the authors introduce the Bayesian attention to the CTR prediction model, which treats attention weights as data‐dependent local random variables and learns their distribution by approximating their posterior distribution. Specifically, the prior knowledge is constructed into the attention weight distribution, and then the posterior inference is utilised to capture the implicit and flexible user intentions. Extensive experiments on public datasets demonstrate that our algorithm outperforms state‐of‐the‐art algorithms. Empirical evidence shows that random attention weights can predict user intentions better than deterministic ones.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, Y., Chen, M., Chen, R., Zhao, C., Yuan, M., & Sun, Z. (2024). Bayesian attention‐based user behaviour modelling for click‐through rate prediction. CAAI Transactions on Intelligence Technology, 9(5), 1320-1330. https://doi.org/10.1049/cit2.12343

Vancouver

Zhang Y, Chen M, Chen R, Zhao C, Yuan M, Sun Z. Bayesian attention‐based user behaviour modelling for click‐through rate prediction. CAAI Transactions on Intelligence Technology. 2024;9(5):1320-1330. doi:10.1049/cit2.12343

BibTeX
@article{Zhang2024,
  author = {Zhang, Yihao and Chen, Mian and Chen, Ruizhen and Zhao, Chu and Yuan, Meng and Sun, Zhu},
  title = {Bayesian attention‐based user behaviour modelling for click‐through rate prediction},
  journal = {CAAI Transactions on Intelligence Technology},
  year = {2024},
  volume = {9},
  number = {5},
  pages = {1320--1330},
  doi = {10.1049/cit2.12343}
}
Kostenlos starten →