English

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.

Keywords

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

R2 v1 2026-06-24T04:15:20.201Z