Toward Bias-Agnostic Recommender Systems: A Universal Generative Framework
ACM Transactions on Information Systems · 30.11.2024 · 42 (6) · 1-30
DOI: 10.1145/3655617 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 25.06.2024. Verfasst von Zhidan Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hubei Province, China.
Abstract (Originalsprache)
User behavior data, such as ratings and clicks, has been widely used to build personalizing models for recommender systems. However, many unflattering factors (e.g., popularity, ranking position, users’ selection) significantly affect the performance of the learned recommendation model. Most existing work on unbiased recommendation addressed these biases from sample granularity (e.g., sample reweighting, data augmentation) or from the perspective of representation learning (e.g., bias-modeling). However, these methods are usually designed for a specific bias, lacking the universal capability to handle complex situations where multiple biases co-exist. Besides, rare work frees itself from laborious and sophisticated debiasing configurations (e.g., propensity scores, imputed values, or user behavior-generating process). Towards this research gap, in this article, we propose a universal G enerative framework for B ias D isentanglement termed as GBD , constantly generating calibration perturbations for the intermediate representations during training to keep them from being affected by the bias. Specifically, a bias-identifier that tries to retrieve the bias-related information from the representations is first introduced. Subsequently, the calibration perturbations are generated to significantly deteriorate the bias-identifier’s performance, making the bias gradually disentangled from the calibrated representations. Therefore, without relying on notorious debiasing configurations, a bias-agnostic model is obtained under the guidance of the bias identifier. We further present its universality by subsuming the representative biases and their mixture under the proposed framework. Finally, extensive experiments on the real-world, synthetic, and semi-synthetic datasets have demonstrated the superiority of the proposed approach against a wide range of recommendation debiasing methods. The code is available at https://github.com/Zhidan-Wang/GBD .
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hubei Province, China
Zitieren
APA
Wang, Z., Zou, L., Li, C., Wang, S., Chen, X., Yin, D., & Liu, W. (2024). Toward Bias-Agnostic Recommender Systems: A Universal Generative Framework. ACM Transactions on Information Systems, 42(6), 1-30. https://doi.org/10.1145/3655617
Vancouver
Wang Z, Zou L, Li C, Wang S, Chen X, Yin D, et al. Toward Bias-Agnostic Recommender Systems: A Universal Generative Framework. ACM Transactions on Information Systems. 2024;42(6):1-30. doi:10.1145/3655617
BibTeX
@article{Wang2024,
author = {Wang, Zhidan and Zou, Lixin and Li, Chenliang and Wang, Shuaiqiang and Chen, Xu and Yin, Dawei and Liu, Weidong},
title = {Toward Bias-Agnostic Recommender Systems: A Universal Generative Framework},
journal = {ACM Transactions on Information Systems},
year = {2024},
volume = {42},
number = {6},
pages = {1--30},
doi = {10.1145/3655617}
}
EUVIMED