We conduct a large-scale comparative study on linearly combining superparent-one-dependence estimators (SPODEs), a popular family of semi-naive Bayesian classifiers. Altogether 16 model selection and weighing schemes, 58 benchmark data sets, as well as various statistical tests are employed. This paper�s main contributions are three-fold. First, it formally presents each scheme�s definition, rationale and time complexity; and hence can serve as a comprehensive reference for researchers interested in ensemble learning. Second, it offers bias-variance analysis for each scheme�s classification error performance. Third, it identifies effective schemes that meet various needs in practice. This leads to accurate and fast classification algorithms with immediate and significant impact on real-world applications. Another important feature of our study is using a variety of statistical tests to evaluate multiple learning methods across multiple data sets.
%0 Journal Article
%1 YangWebbCerquideszKorbBoughtonTing07
%A Yang, Y.
%A Webb, G.I.
%A Cerquides, J.
%A Korb, K.
%A Boughton, J.
%A Ting, K-M.
%C Los Alamitos, CA
%D 2007
%I IEEE Computer Society
%J IEEE Transactions on Knowledge and Data Engineering (TKDE)
%K Conditional Estimation,AODE Probability
%N 12
%P 1652-1665
%T To Select or To Weigh: A Comparative Study of Linear Combination Schemes for SuperParent-One-Dependence Estimators
%V 19
%X We conduct a large-scale comparative study on linearly combining superparent-one-dependence estimators (SPODEs), a popular family of semi-naive Bayesian classifiers. Altogether 16 model selection and weighing schemes, 58 benchmark data sets, as well as various statistical tests are employed. This paper�s main contributions are three-fold. First, it formally presents each scheme�s definition, rationale and time complexity; and hence can serve as a comprehensive reference for researchers interested in ensemble learning. Second, it offers bias-variance analysis for each scheme�s classification error performance. Third, it identifies effective schemes that meet various needs in practice. This leads to accurate and fast classification algorithms with immediate and significant impact on real-world applications. Another important feature of our study is using a variety of statistical tests to evaluate multiple learning methods across multiple data sets.
@article{YangWebbCerquideszKorbBoughtonTing07,
abstract = {We conduct a large-scale comparative study on linearly combining superparent-one-dependence estimators (SPODEs), a popular family of semi-naive Bayesian classifiers. Altogether 16 model selection and weighing schemes, 58 benchmark data sets, as well as various statistical tests are employed. This paper�s main contributions are three-fold. First, it formally presents each scheme�s definition, rationale and time complexity; and hence can serve as a comprehensive reference for researchers interested in ensemble learning. Second, it offers bias-variance analysis for each scheme�s classification error performance. Third, it identifies effective schemes that meet various needs in practice. This leads to accurate and fast classification algorithms with immediate and significant impact on real-world applications. Another important feature of our study is using a variety of statistical tests to evaluate multiple learning methods across multiple data sets.},
added-at = {2016-03-20T05:42:04.000+0100},
address = {Los Alamitos, CA},
author = {Yang, Y. and Webb, G.I. and Cerquides, J. and Korb, K. and Boughton, J. and Ting, K-M.},
biburl = {https://www.bibsonomy.org/bibtex/27763abb085cb253eeb5355508e0c83db/giwebb},
interhash = {f6e69f225cc3a0d95c69fb051e53f40a},
intrahash = {7763abb085cb253eeb5355508e0c83db},
journal = {{IEEE} Transactions on Knowledge and Data Engineering (TKDE)},
keywords = {Conditional Estimation,AODE Probability},
number = 12,
pages = {1652-1665},
publisher = {{IEEE} Computer Society},
timestamp = {2016-03-20T05:42:04.000+0100},
title = {To Select or To Weigh: A Comparative Study of Linear Combination Schemes for SuperParent-One-Dependence Estimators},
volume = 19,
year = 2007
}