Frequent Pattern Mining in Attributed trees

Abstract : Frequent pattern mining is an important data mining task with a broad range of applications. Initially focused on the discovery of frequent itemsets, studies were extended to mine structural forms like sequences, trees or graphs. In this paper, we introduce a new data mining method that consists in mining new kind of patterns in a collection of attributed trees (atrees). Attributed trees are trees in which vertices are associated with itemsets. Mining this type of patterns (called asubtrees), which combines tree mining and itemset mining, requires the exploration of a huge search space. We present several new algorithms for attributed trees mining and show that their implementations can efficiently list frequent patterns in a database of several thousand of attributed trees.
Document type :
Conference papers
Liste complète des métadonnées
Contributor : Claude Pasquier <>
Submitted on : Wednesday, May 13, 2015 - 5:56:55 AM
Last modification on : Tuesday, October 16, 2018 - 1:01:32 AM




Claude Pasquier, Jérémy Sanhes, Frédéric Flouvat, Nazha Selmaoui-Folcher. Frequent Pattern Mining in Attributed trees. Pei, Jian and Tseng, VincentS. and Cao, Longbing and Motoda, Hiroshi and Xu, Guandong. 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD'13), Apr 2013, Gold Coast, Australia. Lecture Notes in Computer Science, 7818, pp.26-37, Advances in Knowledge Discovery and Data Mining. 〈10.1007/978-3-642-37453-1_3〉. 〈hal-01151513〉



Record views