Measuring Fairness in Generative Models
Machine Learning
2021-07-19 v1
Abstract
Deep generative models have made much progress in improving training stability and quality of generated data. Recently there has been increased interest in the fairness of deep-generated data. Fairness is important in many applications, e.g. law enforcement, as biases will affect efficacy. Central to fair data generation are the fairness metrics for the assessment and evaluation of different generative models. In this paper, we first review fairness metrics proposed in previous works and highlight potential weaknesses. We then discuss a performance benchmark framework along with the assessment of alternative metrics.
Cite
@article{arxiv.2107.07754,
title = {Measuring Fairness in Generative Models},
author = {Christopher T. H Teo and Ngai-Man Cheung},
journal= {arXiv preprint arXiv:2107.07754},
year = {2021}
}
Comments
Accepted in ICML 2021 Workshop - Machine Learning for Data: Automated Creation, Privacy, Bias