QMAS

Abstract

This chapter describes a work that uses the background knowledge of the clustering algorithms previously presented in the book to focus on two distinct data mining tasks-the tasks of labeling and summarizing large sets of complex data. Given a large collection of complex objects, very few of which have labels, how can we guess the labels of the remaining majority, and how can we spot those objects that may need brand new labels, different from the existing ones? The work presented here provides answers to these questions. Specifically, this chapter describes in detail QMAS [2], one third algorithm that focuses on data mining in large sets of complex data, which is a fast and scalable solution to the problem of automatically analyzing, labeling and understanding this kind of data.