EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sustainable transparency on recommender systems: Bayesian ranking of images for explainability

Jorge Paz-Ruza, Amparo Alonso-Betanzos, Bertha Guijarro-Berdiñas, Brais Cancela, Carlos Eiras-Franco

Information Fusion · 2024-11 · 111 · 102497

DOI: 10.1016/j.inffus.2024.102497 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information Fusion, 2024-11. Verfasst von Jorge Paz-Ruza und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recommender Systems have become crucial in the modern world, commonly guiding users towards relevant content or products, and having a large influence over the decisions of users and citizens. However, ensuring transparency and user trust in these systems remains a challenge; personalized explanations have emerged as a solution, offering justifications for recommendations. Among the existing approaches for generating personalized explanations, using existing visual content created by users is a promising option to maximize transparency and user trust. State-of-the-art models that follow this approach, despite leveraging highly optimized architectures, employ surrogate learning tasks that do not efficiently model the objective of ranking images as explanations for a given recommendation; this leads to a suboptimal training process with high computational costs that may not be reduced without affecting model performance. This work presents BRIE, a novel model where we leverage Bayesian Pairwise Ranking to enhance the training process, allowing us to consistently outperform state-of-the-art models in six real-world datasets while reducing its model size by up to 64 times and its CO2 emissions by up to 75% in training and inference.

Zitieren

APA

Paz-Ruza, J., Alonso-Betanzos, A., Guijarro-Berdiñas, B., Cancela, B., & Eiras-Franco, C. (2024). Sustainable transparency on recommender systems: Bayesian ranking of images for explainability. Information Fusion, 111, 102497. https://doi.org/10.1016/j.inffus.2024.102497

Vancouver

Paz-Ruza J, Alonso-Betanzos A, Guijarro-Berdiñas B, Cancela B, Eiras-Franco C. Sustainable transparency on recommender systems: Bayesian ranking of images for explainability. Information Fusion. 2024;111:102497. doi:10.1016/j.inffus.2024.102497

BibTeX
@article{PazRuza2024,
  author = {Paz-Ruza, Jorge and Alonso-Betanzos, Amparo and Guijarro-Berdiñas, Bertha and Cancela, Brais and Eiras-Franco, Carlos},
  title = {Sustainable transparency on recommender systems: Bayesian ranking of images for explainability},
  journal = {Information Fusion},
  year = {2024},
  volume = {111},
  pages = {102497},
  doi = {10.1016/j.inffus.2024.102497}
}
Kostenlos starten →