Show simple item record  

dc.contributor.authorvan Rijn, Jan N.en_NZ
dc.contributor.authorHolmes, Geoffreyen_NZ
dc.contributor.authorPfahringer, Bernharden_NZ
dc.contributor.authorVanschoren, Joaquinen_NZ
dc.date.accessioned2019-09-23T23:03:29Z
dc.date.available2018-01-01en_NZ
dc.date.available2019-09-23T23:03:29Z
dc.date.issued2018en_NZ
dc.identifier.citationvan Rijn, J. N., Holmes, G., Pfahringer, B., & Vanschoren, J. (2018). The online performance estimation framework: heterogeneous ensemble learning for data streams. Machine Learning, 107(1), 149–176. https://doi.org/10.1007/s10994-017-5686-9en
dc.identifier.issn0885-6125en_NZ
dc.identifier.urihttps://hdl.handle.net/10289/12906
dc.description.abstractEnsembles of classifiers are among the best performing classifiers available in many data mining applications, including the mining of data streams. Rather than training one classifier, multiple classifiers are trained, and their predictions are combined according to a given voting schedule. An important prerequisite for ensembles to be successful is that the individual models are diverse. One way to vastly increase the diversity among the models is to build an heterogeneous ensemble, comprised of fundamentally different model types. However, most ensembles developed specifically for the dynamic data stream setting rely on only one type of base-level classifier, most often Hoeffding Trees. We study the use of heterogeneous ensembles for data streams. We introduce the Online Performance Estimation framework, which dynamically weights the votes of individual classifiers in an ensemble. Using an internal evaluation on recent training data, it measures how well ensemble members performed on this and dynamically updates their weights. Experiments over a wide range of data streams show performance that is competitive with state of the art ensemble techniques, including Online Bagging and Leveraging Bagging, while being significantly faster. All experimental results from this work are easily reproducible and publicly available online.
dc.format.mimetypeapplication/pdf
dc.language.isoenen_NZ
dc.publisherSpringeren_NZ
dc.rights© The Author(s) 2017. This article is an open access publication
dc.subjectScience & Technologyen_NZ
dc.subjectTechnologyen_NZ
dc.subjectComputer Science, Artificial Intelligenceen_NZ
dc.subjectComputer Scienceen_NZ
dc.subjectData streamsen_NZ
dc.subjectEnsemblesen_NZ
dc.subjectMeta-learningen_NZ
dc.subjectALGORITHM SELECTIONen_NZ
dc.subjectWEIGHTED MAJORITYen_NZ
dc.subjectMachine learning
dc.titleThe online performance estimation framework: heterogeneous ensemble learning for data streamsen_NZ
dc.typeJournal Article
dc.identifier.doi10.1007/s10994-017-5686-9en_NZ
dc.relation.isPartOfMachine Learningen_NZ
pubs.begin-page149
pubs.elements-id216089
pubs.end-page176
pubs.issue1en_NZ
pubs.publication-statusPublisheden_NZ
pubs.volume107en_NZ
dc.identifier.eissn1573-0565en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record