Decomposition methodology for classification tasks

Lior Rokach*, Oded Mainon

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

The idea of decomposition methodology is to break down a complex data mining task into several smaller, less complex and more manageable, sub-tasks that are solvable by using existing tools, then joining their solutions together in order to solve the original problem. In this paper we provide an overview of decomposition methods in classification tasks with emphasis on elementary decomposition methods. We present the main properties that characterize various decomposition frameworks and the advantages of using these framework. Finally we discuss the uniqueness of decomposition methodology as opposed to other closely related fields, such as ensemble methods and distributed data mining.

Original languageEnglish
Title of host publication2005 IEEE International Conference on Granular Computing
Pages636-641
Number of pages6
DOIs
StatePublished - 2005
Event2005 IEEE International Conference on Granular Computing - Beijing, China
Duration: 25 Jul 200527 Jul 2005

Publication series

Name2005 IEEE International Conference on Granular Computing
Volume2005

Conference

Conference2005 IEEE International Conference on Granular Computing
Country/TerritoryChina
CityBeijing
Period25/07/0527/07/05

Fingerprint

Dive into the research topics of 'Decomposition methodology for classification tasks'. Together they form a unique fingerprint.

Cite this