Presentation 2003/7/24
Enumerating Closed Item Sets via Maximal Bipartite Cliques
Takeaki UNO, Hiroki ARIMURA, Tatsuya ASAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For an item set and its subset family, a frequent set is a subset of the item set included in at least a specified number of elements of the subset family. Frequent sets have some applications in data mining. Recently, maximal frequent set and closed item sets are remarked where a closed item set is a group of similar frequent sets, since we can obtain necessary frequent sets by enumerating closed item sets. In this paper, we propose an efficient method for enumerating closed item sets by using enumeration of maximal bipartite cliques, and enumeration algo- rithm for maximal frequent sets via closed item sets. We evaluate their performances by computational experiments using benchmark problems, and show that our algorithms are faster than existing algorithms. Key words
Keyword(in Japanese) (See Japanese page)
Keyword(in English) listing / generation / frequent set mining / algorithm / complexity / sparse graph / data mining
Paper # AI2003-13
Date of Issue

Conference Information
Committee AI
Conference Date 2003/7/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Enumerating Closed Item Sets via Maximal Bipartite Cliques
Sub Title (in English)
Keyword(1) listing
Keyword(2) generation
Keyword(3) frequent set mining
Keyword(4) algorithm
Keyword(5) complexity
Keyword(6) sparse graph
Keyword(7) data mining
1st Author's Name Takeaki UNO
1st Author's Affiliation National Institute of Informatics()
2nd Author's Name Hiroki ARIMURA
2nd Author's Affiliation Information Science and Electrical Engineering, Kyushu University
3rd Author's Name Tatsuya ASAI
3rd Author's Affiliation Information Science and Electrical Engineering, Kyushu University
Date 2003/7/24
Paper # AI2003-13
Volume (vol) vol.103
Number (no) 243
Page pp.pp.-
#Pages 6
Date of Issue