Generative Structure Learning for Markov Logic Networks

In this paper, we present a generative algorithm to learn Markov Logic Network (MLN) structures automatically, directly from a training dataset. The algorithm follows a bottom-up approach by first heuristically transforming the training dataset into boolean tables, then creating candidate clauses using these boolean tables and finally choosing the best clauses to build the MLN. Comparisons to the state-of-the-art structure learning algorithms for MLNs in two real-world domains show that the proposed algorithm outperforms them in terms of the conditional log likelihood (CLL), and the area under the precision-recall curve (AUC).