NAACL 2022long27 citations

Optimising Equal Opportunity Fairness in Model Training

Aili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin, Lea Frermann

Abstract

Real-world datasets often encode stereotypes and societal biases. Such biases can be implicitly captured by trained models, leading to biased predictions and exacerbating existing societal preconceptions. Existing debiasing methods, such as adversarial training and removing protected information from representations, have been shown to reduce bias. However, a disconnect between fairness criteria and training objectives makes it difficult to reason theoretically about the effectiveness of different techniques. In this work, we propose two novel training objectives which directly optimise for the widely-used criterion of equal opportunity, and show that they are effective in reducing bias while maintaining high performance over two classification tasks.

BibTeX
@inproceedings{shen-etal-2022-optimising,
    title = "Optimising Equal Opportunity Fairness in Model Training",
    author = "Shen, Aili  and
      Han, Xudong  and
      Cohn, Trevor  and
      Baldwin, Timothy  and
      Frermann, Lea",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-main.299/",
    doi = "10.18653/v1/2022.naacl-main.299",
    pages = "4073--4084"
}
Optimising Equal Opportunity Fairness in Model Training · NAACL 2022