Fairness GAN

2018/05/24 by Prasanna Sattigeri, Sattigeri, Prasanna, Samuel C. Hoffman +5 · 1 citation
Social Sciences · #Computers and Society (cs.CY) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1805.09910

openalex publication_date 2018/05/24 · openalex created_date 2024/04/11 · openalex updated_date 2026/07/28

Abstract

In this paper, we introduce the Fairness GAN, an approach for generating a dataset that is plausibly similar to a given multimedia dataset, but is more fair with respect to protected attributes in allocative decision making. We propose a novel auxiliary classifier GAN that strives for demographic parity or equality of opportunity and show empirical results on several datasets, including the CelebFaces Attributes (CelebA) dataset, the Quick, Draw! dataset, and a dataset of soccer player images and the offenses they were called for. The proposed formulation is well-suited to absorbing unlabeled data; we leverage this to augment the soccer dataset with the much larger CelebA dataset. The methodology tends to improve demographic parity and equality of opportunity while generating plausible images.

Cited by

• Behind the Screens: Uncovering Bias in AI-Driven Video Interview Assessments Using Counterfactuals

Related

• Fair Attribute Classification through Latent Space De-biasing
• FairGAN: Fairness-aware Generative Adversarial Networks
• RepFair-GAN: Mitigating Representation Bias in GANs Using Gradient Clipping
• Fair GANs through model rebalancing for extremely imbalanced class distributions
• Configurable Fairness: Direct Optimization of Parity Metrics via Vision-Language Models