# On the Impact of Class Imbalance in GP Streaming Classification with Label Budgets

Created by W.Langdon from gp-bibliography.bib Revision:1.4340

@InProceedings{khanchi:2016:EuroGP,
author =       "Sara Khanchi and Malcolm Iain Heywood and
Nur Zincir-Heywood",
title =        "On the Impact of Class Imbalance in GP Streaming
Classification with Label Budgets",
booktitle =    "EuroGP 2016: Proceedings of the 19th European
Conference on Genetic Programming",
year =         "2016",
month =        "30 " # mar # "--1 " # apr,
editor =       "Malcolm I. Heywood and James McDermott and
Mauro Castelli and Ernesto Costa and Kevin Sim",
series =       "LNCS",
volume =       "9594",
publisher =    "Springer Verlag",
pages =        "35--50",
organisation = "EvoStar",
keywords =     "genetic algorithms, genetic programming",
isbn13 =       "978-3-319-30668-1",
DOI =          "doi:10.1007/978-3-319-30668-1_3",
abstract =     "Streaming data scenarios introduce a set of
requirements that do not exist under supervised
classification. Specific examples include, anytime
operation, non-stationary processes, and limited label
budgets. From the perspective of class imbalance, this
implies that it is not even possible to guarantee that
all classes are present in the samples of data used to
construct a model. Moreover, when decisions are made
regarding what subset of data to sample, no label
information is available. Only after sampling is label
information provided. This represents a more
challenging task than encountered under non-streaming
(offline) scenarios because the training partition
contains label information. In this work, we
investigate the utility of different protocols for
sampling from the stream under the above constraints.
Adopting a uniform sampling protocol was previously
shown to be reasonably effective under both
evolutionary and non-evolutionary streaming
classifiers. In this work, we introduce a scheme for
using the current champion classifier to bias the
sampling of training instances \textit{during} the
course of the stream. The resulting streaming framework
for genetic programming is more effective at sampling
minor classes and therefore reacting to changes in the
underlying process responsible for generating the data
stream.",
notes =        "Part of \cite{Heywood:2016:GP} EuroGP'2016 held in
conjunction with EvoCOP2016, EvoMusArt2016 and
EvoApplications2016",
}



Genetic Programming entries for Sara Khanchi Malcolm Heywood Nur Zincir-Heywood

Citations