Back to Search
Start Over
Optimising Equal Opportunity Fairness in Model Training
- Publication Year :
- 2022
-
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 {\it equal opportunity}, and show that they are effective in reducing bias while maintaining high performance over two classification tasks.<br />Comment: Accepted to NAACL 2022 main conference
- Subjects :
- Computer Science - Machine Learning
Computer Science - Computation and Language
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2205.02393
- Document Type :
- Working Paper