EUVIMEDEUVIMED entdecken
Crossref

MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge

Maxwell J. Yin, Boyu Wang, Charles Ling

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (24) · 25724-25732

DOI: 10.1609/aaai.v39i24.34764 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Maxwell J. Yin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Models trained on real-world data often mirror and exacerbate existing social biases. Traditional methods for mitigating these biases typically require prior knowledge of the specific biases to be addressed, and the social groups associated with each instance. In this paper, we introduce a novel adversarial training strategy that operates withour relying on prior bias-type knowledge (e.g., gender or racial bias) and protected attribute labels. Our approach dynamically identifies biases during model training by utilizing auxiliary bias detector. These detected biases are simultaneously mitigated through adversarial training. Crucially, we implement these bias detectors at various levels of the feature maps of the main model, enabling the detection of a broader and more nuanced range of bias features. Through experiments on racial and gender biases in sentiment and occupation classification tasks, our method effectively reduces social biases without the need for demographic annotations. Moreover, our approach not only matches but often surpasses the efficacy of methods that require detailed demographic insights, marking a significant advancement in bias mitigation techniques.

Zitieren

APA

Yin, M. J., Wang, B., & Ling, C. (2025). MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge. Proceedings of the AAAI Conference on Artificial Intelligence, 39(24), 25724-25732. https://doi.org/10.1609/aaai.v39i24.34764

Vancouver

Yin MJ, Wang B, Ling C. MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(24):25724-25732. doi:10.1609/aaai.v39i24.34764

BibTeX
@article{Yin2025,
  author = {Yin, Maxwell J. and Wang, Boyu and Ling, Charles},
  title = {MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {24},
  pages = {25724--25732},
  doi = {10.1609/aaai.v39i24.34764}
}
Kostenlos starten →