Decision functions for chain classifiers based on Bayesian networks for multi-label classification

Varando, Gherardo and Bielza Lozoya, María Concepción and Larrañaga Múgica, Pedro María (2015). Decision functions for chain classifiers based on Bayesian networks for multi-label classification. "International Journal of Approximate Reasoning", v. 68 (n. c); pp. 164-178. ISSN 0888-613X. https://doi.org/10.1016/j.ijar.2015.06.006.

Description

Title: Decision functions for chain classifiers based on Bayesian networks for multi-label classification
Author/s:
  • Varando, Gherardo
  • Bielza Lozoya, María Concepción
  • Larrañaga Múgica, Pedro María
Item Type: Article
Título de Revista/Publicación: International Journal of Approximate Reasoning
Date: 2015
ISSN: 0888-613X
Volume: 68
Subjects:
Freetext Keywords: Bayesian network classifier; Multi-label classification; Expressive power; Chain classifier; Binary relevance; Decision functions
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (848kB) | Preview

Abstract

Multi-label classification problems require each instance to be assigned a subset of a defined set of labels. This problem is equivalent to finding a multi-valued decision function that predicts a vector of binary classes. In this paper we study the decision boundaries of two widely used approaches for building multi-label classifiers, when Bayesian networkaugmented naive Bayes classifiers are used as base models: Binary relevance method and chain classifiers. In particular extending previous single-label results to multi-label chain classifiers, we find polynomial expressions for the multi-valued decision functions associated with these methods. We prove upper boundings on the expressive power of both methods and we prove that chain classifiers provide a more expressive model than the binary relevance method.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainC080020-09UnspecifiedUniversidad Politécnica de MadridCajal Blue Brain
Government of SpainTIN2013-41592-PUnspecifiedUniversidad Politécnica de MadridAPRENDIZAJE DE REDES BAYESIANAS CON VARIABLES SIN Y CON DIRECCIONALIDAD PARA DESCUBRIMIENTO DE ASOCIACIONES, PREDICCION MULTIRESPUESTA Y CLUSTERING
Madrid Regional GovernmentS2013/ICE-2845CASI-CAM-CMUnspecifiedConceptos y Aplicaciones de los Sistemas Inteligentes

More information

Item ID: 41022
DC Identifier: http://oa.upm.es/41022/
OAI Identifier: oai:oa.upm.es:41022
DOI: 10.1016/j.ijar.2015.06.006
Official URL: http://www.sciencedirect.com/science/article/pii/S0888613X15000900
Deposited by: Memoria Investigacion
Deposited on: 31 Oct 2016 13:08
Last Modified: 06 Jun 2019 13:31
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM