final-author-version.pdf (7.92 MB)
Online Ensemble Learning of Data Streams with Gradually Evolved Classes
journal contribution
posted on 2016-02-16, 11:35 authored by Y. Sun, K. Tang, Leandro Lei Minku, S. Wang, X. YaoClass evolution, the phenomenon of class emergence and disappearance, is an important research topic for data stream mining. All previous studies implicitly regard class evolution as a transient change, which is not true for many real-world problems. This paper concerns the scenario where classes emerge or disappear gradually. A class-based ensemble approach, namely Class-Based ensemble for Class Evolution (CBCE), is proposed. By maintaining a base learner for each class and dynamically updating the base learners with new data, CBCE can rapidly adjust to class evolution. A novel under-sampling method for the base learners is also proposed to handle the dynamic class-imbalance problem caused by the gradual evolution of classes. Empirical studies demonstrate the effectiveness of CBCE in various class evolution scenarios in comparison to existing class evolution adaptation methods.
History
Citation
IEEE Transactions on Knowledge and Data Engineering, 2016, 28 (6), pp. 1532-1545Author affiliation
/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Computer ScienceVersion
- AM (Accepted Manuscript)
Published in
IEEE Transactions on Knowledge and Data EngineeringPublisher
Institute of Electrical and Electronics Engineers (IEEE), United Statesissn
1041-4347Acceptance date
2016-01-27Copyright date
2016Available date
2016-02-16Publisher DOI
Publisher version
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7401075Language
enAdministrator link
Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC