DDD: A new ensemble approach for dealing with concept drift

Leandro L. MINKU, Xin YAO

Research output: Journal PublicationsJournal Article (refereed)peer-review

358 Citations (Scopus)

Abstract

Online learning algorithms often have to operate in the presence of concept drifts. A recent study revealed that different diversity levels in an ensemble of learning machines are required in order to maintain high generalization on both old and new concepts. Inspired by this study and based on a further study of diversity with different strategies to deal with drifts, we propose a new online ensemble learning approach called Diversity for Dealing with Drifts (DDD). DDD maintains ensembles with different diversity levels and is able to attain better accuracy than other approaches. Furthermore, it is very robust, outperforming other drift handling approaches in terms of accuracy when there are false positive drift detections. In all the experimental comparisons we have carried out, DDD always performed at least as well as other drift handling approaches under various conditions, with very few exceptions. © 2012 IEEE.
Original languageEnglish
Article number5719616
Pages (from-to)619-633
Number of pages15
JournalIEEE Transactions on Knowledge and Data Engineering
Volume24
Issue number4
Early online date24 Feb 2011
DOIs
Publication statusPublished - Apr 2012
Externally publishedYes

Keywords

  • Concept drift
  • diversity
  • ensembles of learning machines
  • online learning

Fingerprint

Dive into the research topics of 'DDD: A new ensemble approach for dealing with concept drift'. Together they form a unique fingerprint.

Cite this