Optimising Equal Opportunity Fairness in Model Training

Authors

Aili Shen, School of Computing and Information Systems, The University of Melbourne, Victoria, 3010, Australia
Xudong Han, School of Computing and Information Systems, The University of Melbourne, Victoria, 3010, Australia
Trevor Cohn, School of Computing and Information Systems, The University of Melbourne, Victoria, 3010, Australia
Timothy Baldwin, The University of Melbourne, Australia & Mohamed bin Zayed University of Artificial IntelligenceFollow
Lea Frermann, School of Computing and Information Systems, The University of Melbourne, Victoria, 3010, Australia

Document Type

Article

Publication Title

arXiv

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. Copyright © 2022, The Authors. All rights reserved.

DOI

10.48550/arXiv.2205.02393

Publication Date

4-4-2022

Keywords

Classification tasks, De-biasing, Equal opportunity, Fairness criterion, Model training, Performance, Real-world datasets, Machine learning, Computation and Language (cs.CL), Machine Learning (cs.LG)

Comments

IR Deposit conditions: non-described

Preprint available on arXiv

Recommended Citation

A. Shen, X. Han, T. Cohn, T. Baldwin, and L. Frermann, "Optimising Equal Opportunity Fairness in Model Training", 2022, arXiv:2205.02393