On the Fairness of Generative Adversarial Networks (GANs)

Generative adversarial networks (GANs) are one of the greatest advances in AI in recent years. With their ability to directly learn the probability distribution of data and then sample synthetic realistic data. Many applications have emerged, using GANs to solve classical problems in machine learning, such as data augmentation, class imbalance problems, and fair representation learning. In this paper, we analyze and highlight the fairness concerns of GANs. In this regard, we show empirically that GANs models may inherently prefer certain groups during the training process and therefore they’re not able to homogeneously generate data from different groups during the testing phase. Furthermore, we propose solutions to solve this issue by conditioning the GAN model towards samples’ groups or using the ensemble method (boosting) to allow the GAN model to leverage distributed structure of data during the training phase and generate groups at an equal rate during the testing phase.