Closed and Maximal Tree Mining Using Natural Representations

Closure-based mining on purely relational data, that is, itemset mining, is, by now, well-established, and there are interesting algorithmic developments. Sharing some of the attractive features of frequency-based summarization of subsets, it offers an alternative view with both downsides and advantages; among the latter, there are the facts that, first, by imposing closure, the number of frequent sets is heavily reduced and, second, the possibility appears of developing a mathematical foundation that connects closure-based mining with lattice-theoretic approaches like Formal Concept Analysis.