Feature Selection for Propositionalization

Following the success of inductive logic programming on structurally complex but small problems, recently there has been strong interest in relational methods that scale to real-world databases. Propositionalization has already been shown to be a particularly promising approach for robustly and effectively handling larger relational data sets. However, the number of propositional features generated here tends to quickly increase, e.g. with the number of relations, with negative effects especially for the efficiency of learning. In this paper, we show that feature selection techniques can significantly increase the efficiency of transformation-based learning without sacrificing accuracy.