Efficient Monte Carlo optimization for multi-label classifier chains

Luengo García, David and Read, Jesse and Martino, Luca (2013). Efficient Monte Carlo optimization for multi-label classifier chains. In: "38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)", 26/05/2013 - 31/05/2013, Vancouver (Canadá). ISBN 978-1-4799-0356-6. pp. 3457-3461.

Description

Title: Efficient Monte Carlo optimization for multi-label classifier chains
Author/s:
  • Luengo García, David
  • Read, Jesse
  • Martino, Luca
Item Type: Presentation at Congress or Conference (Article)
Event Title: 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Event Dates: 26/05/2013 - 31/05/2013
Event Location: Vancouver (Canadá)
Title of Book: Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013)
Date: 2013
ISBN: 978-1-4799-0356-6
Subjects:
Freetext Keywords: multi-label classification; Monte Carlo methods; classifier chains
Faculty: E.U.I.T. Telecomunicación (UPM)
Department: Ingeniería de Circuitos y Sistemas [hasta 2014]
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 (587kB) | Preview

Abstract

Multi-label classification (MLC) is the supervised learning problem where an instance may be associated with multiple labels. Modeling dependencies between labels allows MLC methods to improve their performance at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies. On the one hand, the original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors down the chain. On the other hand, a recent Bayes-optimal method improves the performance, but is computationally intractable in practice. Here we present a novel double-Monte Carlo scheme (M2CC), both for finding a good chain sequence and performing efficient inference. The M2CC algorithm remains tractable for high-dimensional data sets and obtains the best overall accuracy, as shown on several real data sets with input dimension as high as 1449 and up to 103 labels.

More information

Item ID: 33285
DC Identifier: http://oa.upm.es/33285/
OAI Identifier: oai:oa.upm.es:33285
Official URL: https://www2.securecms.com/ICASSP2013/default.asp
Deposited by: Memoria Investigacion
Deposited on: 15 Apr 2015 16:05
Last Modified: 15 Apr 2015 17:16
  • 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