Knowledge-Based Regularization in Generative Modeling
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Main track. Pages 2390-2396. https://doi.org/10.24963/ijcai.2020/331
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.
Machine Learning: Knowledge-based Learning
Machine Learning: Learning Generative Models
Machine Learning: Deep Generative Models