高维数据的频繁封闭模式挖掘算法研究综述

Mining Frequent Closed Patterns for Very High Dimensional Data:A Review

挖掘频繁模式是数据挖掘领域一个重要且基础的问题。频繁封闭项集挖掘可以提供完全的无冗余的频繁模式。随着生物信息学的兴起,产生了一类具有较多列数的特殊数据集,这种高维数据集对以前的频繁封闭模式挖掘算法提出了新的挑战。对高维数据的频繁封闭模式挖掘算法进行了综述,按照算法的特性对这些算法进行了分类,比较了基于行计数的两类挖掘算法,并对能根据数据子集的特性进行列计数和行计数自动转换的混合计数算法进行了讨论,最后指出了该领域的研究方向。

Mining frequent patterns is a fundamental and essential problem in many data mining applications. Mining frequent closed itemsets provides complete and non-redundant results for frequent pattern analysis. The growth of bioinformatics has resulted in datasets with new characteristics. These datasets typically contain a large number of columns. Such high-dimendional datasets pose a great challenge for existing closed frequent pattern discovery algorithms. This paper presents a survey of the various algorithms for mining frequent closed itemsets in very high dimensional data along with a hierarchy organizing the algorithms by their characteristics. We compare two row enumeration-based algorithms, discuss an algorithm which is designed to automatically switch between feature enumeration and row enumeration during the mining process based on the characteristics of the data subset being considered, and finally point out the research direction in this field.