On the Fairness of Generative Adversarial Networks (GANs)
This addresses fairness concerns in GANs for applications like data augmentation and representation learning, but it is incremental as it builds on existing GAN methods.
The paper tackles the problem of fairness in Generative Adversarial Networks (GANs), showing empirically that GANs may inherently prefer certain groups during training and fail to generate data homogeneously from different groups, and proposes solutions like conditioning or ensemble methods to address this issue.
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 unbalance problems, and fair representation learning. In this paper, we analyze and highlight fairness concerns of GANs model. 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' group or using ensemble method (boosting) to allow the GAN model to leverage distributed structure of data during the training phase and generate groups at equal rate during the testing phase.