Hierarchical VampPrior Variational Fair Auto-Encoder
This addresses fairness in decision-making for applications using machine learning, but it is incremental as it builds on existing deep generative models.
The paper tackled the problem of learning fair representations to remove sensitive information from decision-making by proposing a hierarchical Variational Auto-Encoder with mutual information regularization. The result showed that the approach outperforms or matches the current best model on two benchmark datasets in scenarios with fully and partially observable sensitive variables.
Decision making is a process that is extremely prone to different biases. In this paper we consider learning fair representations that aim at removing nuisance (sensitive) information from the decision process. For this purpose, we propose to use deep generative modeling and adapt a hierarchical Variational Auto-Encoder to learn these fair representations. Moreover, we utilize the mutual information as a useful regularizer for enforcing fairness of a representation. In experiments on two benchmark datasets and two scenarios where the sensitive variables are fully and partially observable, we show that the proposed approach either outperforms or performs on par with the current best model.