A number of vertical mining algorithms have been proposed recently for association mining, which have shown to be very e ective and usually outperform horizontal approaches. The main advantage of the vertical format is support for fast frequency counting via intersection operations on transaction ids (tids) and automatic pruning of irrelevant data. The main problem with these approaches is when intermediate results of vertical tid lists become too large for memory, thus a ecting the algorithm scalability.
In this paper we present a novel vertical data representation called Di set, that only keeps track of di erences in the tids of a candidate pattern from its generating frequent patterns. We show that di sets drastically cut down the size of memory required to store intermediate results. We show how di sets, when incorporated into previous vertical mining methods, increase the performance signi cantly. |
