MaPle: a fast algorithm for maximal pattern-based clustering

摘要: Pattern-based clustering is important in many applications, such as DNA micro-array data analysis, automatic recommendation systems and target marketing systems. However, pattern-based large databases challenging. On the one hand, there can be a huge number of clusters them redundant thus make ineffective. other previous proposed methods may not efficient or scalable mining databases. We study problem maximal clustering. Redundant are avoided completely by only clusters. MaPle, an algorithm developed. It conducts depth-first, divide-and-conquer search prunes unnecessary branches smartly. Our extensive performance on both synthetic sets real shows that effective. reduces substantially. Moreover, MaPle more than previously