FairGAN: Fairness-aware Generative Adversarial Networks
This addresses fairness in data generation for data mining applications, but it appears incremental as it builds on existing GAN methods.
The paper tackles the problem of generating discrimination-free data by proposing FairGAN, a fairness-aware generative adversarial network that produces fair data while preserving utility, and experiments on a real dataset demonstrate its effectiveness.
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.