Retour

G-2008-13

Using Heuristics to Speed Up Frequent Pattern Mining

, , et

référence BibTeX

In this paper we present a simple technique that uses background information to improve mining the frequent patterns of structured data. This technique uses a heuristic function that remaps the search space in a way the greatly reduces the number of costly subgraph isomorphism tests, without using space-expensive data structures. We illustrate our approach on a popular structured data mining problem, called the frequent subgraph mining problem, and show, through experiments on synthetic and real-life data, that this simple approach has advantages over other frequent pattern mining algorithms.

, 17 pages

Axes de recherche

Applications de recherche

Publication

Improving constrained pattern mining with first-fail-based heuristics
, , et
Data Mining and Knowledge Discovery, 23(1), 63–90, 2011 référence BibTeX