A soft version of predicate invention based on structured sparsity
William Yang Wang, Kathryn Mazaitis, William W. Cohen · 2015
In predicate invention (PI), new predicates are in-troduced into a logical theory, usually by rewriting a group of closely-related rules to use a common invented predicate as a “subroutine”. PI is difficult, since a poorly-chosen invented predicate may lead to error cascades. Here we suggest a “soft ” version of predicate invention: instead of explicitly creating new predicates, we implicitly group closely-related rules by using structured sparsity to regularize their parameters together. We show that soft PI, unlike hard PI, consistently improves over previous strong baselines for structure-learning on two large-scale tasks. 1