关键词: 数据挖掘 精简集 频繁项目集

Abstract:

Given a large set of data, extracting frequent itemsets in this set is a challenging job in data mining. Many efficient algorithms have been proposed  in the literature. The idea presented in this paper is to extract a condensed representation of the frequent itemsets called disjunction-free sets, instead of extracting the whole frequent itemsets collection. We show that this condensed representation can be used to regenerate all frequent iternsets and their exact frequencies without any access to the original data. An algorithm, HOPE-Ⅱ, is presented to extract the frequent disjunction-free sets andd practical experiments show that this representation can be extracted very efficiently. We compare it with another representation in the literature cal led frequent closed sets, and in nearly all the experiments we have done, the disjunction-free sets have been extracted much more efficiently than the f requent closed sets.

Key words: （data mining, condensed representation;frequent itemset.）