On reducing classifier granularity in mining concept-drifting data streams

Peng Wang, Haixun Wang, Xiaochen Wu, Wei Wang, Baile Shi

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

16 Scopus citations

Abstract

Many applications use classification models on streaming data to detect actionable alerts. Due to concept drifts in the underlying data, how to maintain a model's uptodateness has become one of the most challenging tasks in mining data streams. State of the art approaches, including both the incrementally updated classifiers and the ensemble classifiers, have proved that model update is a very costly process. In this paper, we introduce the concept of model granularity. We show that reducing model granularity will reduce model update cost. Indeed, models of fine granularity enable us to efficiently pinpoint local components in the model that are affected by the concept drift. It also enables us to derive new components that can easily integrate with the model to reflect the current data distribution, thus avoiding expensive updates on a global scale. Experiments on real and synthetic data show that our approach is able to maintain good prediction accuracy at a fraction of model updating cost of state of the art approaches.

Original languageEnglish
Title of host publicationProceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005
Pages474-481
Number of pages8
DOIs
StatePublished - 2005
Externally publishedYes
Event5th IEEE International Conference on Data Mining, ICDM 2005 - Houston, TX, United States
Duration: 27 Nov 200530 Nov 2005

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
ISSN (Print)1550-4786

Conference

Conference5th IEEE International Conference on Data Mining, ICDM 2005
Country/TerritoryUnited States
CityHouston, TX
Period27/11/0530/11/05

Fingerprint

Dive into the research topics of 'On reducing classifier granularity in mining concept-drifting data streams'. Together they form a unique fingerprint.

Cite this