The paper describes a novel way of regularizing a deep neural network to be semantically similar to a logical formula. The main contribution is the use of d-DDNF, a particular format for formula which is well-suited to embedding in a graph CNN. This format is used in certain reasoning tasks, but is not widely known in the NeurIPS community, and (to this metareviewer at least) seeing it in this context was surprising and insightful. It also seems to be a trick that could be useful across a range of tasks. It is shown that the model improves performance on synthetic data and a non-trivial realistic task, visual relation prediction. The paper is well-written, and judged to contain results of some significance by all reviewers, and one of the reviewers also rated the paper as a strong accept.