# FairGAN: Fairness-aware Generative Adversarial Networks Source: [FairGAN: Fairness-aware Generative Adversarial Networks]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:04:03.574Z Authors: Depeng Xu, Shuhan Yuan, Lu Zhang, Xintao Wu Published: 2018-05-28T23:50:20.000Z ## Abstract Fairness-aware learning is increasingly important in data mining. Discrimination prevention aims to prevent discrimination in the training data before it is used to conduct predictive analysis. In this paper, we focus on fair data generation that ensures the generated data is discrimination free. Inspired by generative adversarial networks (GAN), we present fairness-aware generative adversarial networks, called FairGAN, which are able to learn a generator producing fair data and also preserving good data utility. Compared with the naive fair data generation models, FairGAN further ensures the classifiers which are trained on generated data can achieve fair classification on real data. Experiments on a real dataset show the effectiveness of FairGAN. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Fairness-aware Synthetic Data Generation on Adult dataset](): Fairness-aware Synthetic Data Generation; Adult dataset; Precision: 0.681. - [Credit approval prediction on Credit Approval dataset (test)](): Credit approval prediction; Credit Approval dataset (test); AUROC: 0.68. ## Original sources and implementation [Original paper]() [PDF]()