Constraint-Based Mining and Inductive Databases pages:38-63
Various definitions and frameworks for discovering frequent trees in forests have been developed recently. At the heart of these frameworks lies the notion of matching, which determines if a pattern tree matches a tree in a data set. We compare four notions of tree matching for use in frequent tree mining and show how they are related to each other. Furthermore, we show how Zaki's TreeMinerV algorithm can be adapted to employ three of the four notions of tree matching. Experiments on synthetic and real world data highlight the differences between the matchings.