Knowledge-Based Regularization in Generative Modeling
This work addresses the challenge of efficiently integrating domain knowledge into generative modeling for researchers and practitioners, though it is incremental as it builds on existing methods.
The paper tackles the problem of incorporating prior knowledge of feature relations into general-purpose generative models by proposing a regularizer that enforces prescribed relative dependence of features in the marginals. It demonstrates effectiveness across multiple datasets and generative models, including variational autoencoders and generative adversarial networks.
Prior domain knowledge can greatly help to learn generative models. However, it is often too costly to hard-code prior knowledge as a specific model architecture, so we often have to use general-purpose models. In this paper, we propose a method to incorporate prior knowledge of feature relations into the learning of general-purpose generative models. To this end, we formulate a regularizer that makes the marginals of a generative model to follow prescribed relative dependence of features. It can be incorporated into off-the-shelf learning methods of many generative models, including variational autoencoders and generative adversarial networks, as its gradients can be computed using standard backpropagation techniques. We show the effectiveness of the proposed method with experiments on multiple types of datasets and generative models.