Presentation	2004/7/7 Adaptive Load Balancing on Tree Based Parallel Frequent Pattern Mining Iko PRAMUDIONO, Masaru KITSUREGAWA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Adaptability is a major challenge to efficiently mine frequent patterns from large scale databases. We develop FP-growth based parallel mining algorithms on a PC cluster. Since the FP-tree is a complex data structure, it is difficult to partition and also increases the processing skew among nodes. The parallel algorithm employs a parameter called "path-depth" to estimate the workload from the minimum length of the tree-branches that possibly become frequent. Since the path depth is a data dependent parameter, we develop adaptive approaches to dynamically adjust the parameter during the execution.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	frequent pattern mining / parallel processing / PC cluster / load balancing
Paper #	DE2004-85
Date of Issue

Conference Information
Committee	DE
Conference Date	2004/7/7(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	Data Engineering (DE)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Adaptive Load Balancing on Tree Based Parallel Frequent Pattern Mining
Sub Title (in English)
Keyword(1)	frequent pattern mining
Keyword(2)	parallel processing
Keyword(3)	PC cluster
Keyword(4)	load balancing
1st Author's Name	Iko PRAMUDIONO
1st Author's Affiliation	NTT Information Sharing Platform Laboratories, NTT Corporation()
2nd Author's Name	Masaru KITSUREGAWA
2nd Author's Affiliation	Institute of Industrial Science, The University of Tokyo
Date	2004/7/7
Paper #	DE2004-85
Volume (vol)	vol.104
Number (no)	177
Page	pp.pp.-
#Pages	6
Date of Issue