Fair GANs through model rebalancing for extremely imbalanced class distributions
This work addresses fairness issues in generative models for applications like facial generation, though it is incremental as it builds on existing GAN frameworks.
The paper tackles the problem of bias in deep generative models caused by imbalanced training data by introducing a model rebalancing approach using an evolutionary algorithm and a bias mitigation loss function. The method improves fairness metrics by almost 5 times on a racial fairness task while maintaining image quality, and achieves comparable results on an imbalanced CIFAR10 dataset as training on a balanced dataset twice as large.
Deep generative models require large amounts of training data. This often poses a problem as the collection of datasets can be expensive and difficult, in particular datasets that are representative of the appropriate underlying distribution (e.g. demographic). This introduces biases in datasets which are further propagated in the models. We present an approach to construct an unbiased generative adversarial network (GAN) from an existing biased GAN by rebalancing the model distribution. We do so by generating balanced data from an existing imbalanced deep generative model using an evolutionary algorithm and then using this data to train a balanced generative model. Additionally, we propose a bias mitigation loss function that minimizes the deviation of the learned class distribution from being equiprobable. We show results for the StyleGAN2 models while training on the Flickr Faces High Quality (FFHQ) dataset for racial fairness and see that the proposed approach improves on the fairness metric by almost 5 times, whilst maintaining image quality. We further validate our approach by applying it to an imbalanced CIFAR10 dataset where we show that we can obtain comparable fairness and image quality as when training on a balanced CIFAR10 dataset which is also twice as large. Lastly, we argue that the traditionally used image quality metrics such as Frechet inception distance (FID) are unsuitable for scenarios where the class distributions are imbalanced and a balanced reference set is not available.