English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Efficiently Discovering Locally Exceptional yet Globally Representative Subgroups

MPS-Authors
/persons/resource/persons134204

Kalofolias,  Janis
Databases and Information Systems, MPI for Informatics, Max Planck Society;

/persons/resource/persons188983

Boley,  Mario
Databases and Information Systems, MPI for Informatics, Max Planck Society;

/persons/resource/persons79525

Vreeken,  Jilles
Databases and Information Systems, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1709.07941.pdf
(Preprint), 508KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Kalofolias, J., Boley, M., & Vreeken, J. (2017). Efficiently Discovering Locally Exceptional yet Globally Representative Subgroups. Retrieved from http://arxiv.org/abs/1709.07941.


Cite as: http://hdl.handle.net/11858/00-001M-0000-002E-0685-D
Abstract
Subgroup discovery is a local pattern mining technique to find interpretable descriptions of sub-populations that stand out on a given target variable. That is, these sub-populations are exceptional with regard to the global distribution. In this paper we argue that in many applications, such as scientific discovery, subgroups are only useful if they are additionally representative of the global distribution with regard to a control variable. That is, when the distribution of this control variable is the same, or almost the same, as over the whole data. We formalise this objective function and give an efficient algorithm to compute its tight optimistic estimator for the case of a numeric target and a binary control variable. This enables us to use the branch-and-bound framework to efficiently discover the top-$k$ subgroups that are both exceptional as well as representative. Experimental evaluation on a wide range of datasets shows that with this algorithm we discover meaningful representative patterns and are up to orders of magnitude faster in terms of node evaluations as well as time.