DATA MINING: PATTERN MINING AS A CLIQUE EXTRACTING TASK

摘要

One of the important tasks in solving data mining problems is finding frequent patterns in a given dataset. It allows to handle several tasks such as pattern mining, discovering association rules, clustering etc. There are several algorithms to solve this problem. In this paper we describe our task and results: a method for reordering a data matrix to give it a more informative form, problems of large datasets, (frequent) pattern finding task. Finally we show how to treat a data matrix as a graph, a pattern as a clique and pattern mining process as a clique extracting task. We present also a fast diclique extracting algorithm for pattern mining.