Efficient monte carlo methods for multi-dimensional learning with classifier chains

PATTERN RECOGNITION

卷:47

Article

Read, Jesse¹  Martino, Luca¹  Luengo, David² 

[1] Univ Carlos III Madrid, Dept Signal Theory & Commun, Madrid 28911, Spain

[2] Univ Politecn Madrid, Dept Circuits & Syst Engn, Madrid 28031, Spain

关键词: Classifier chains;    Multi-dimensional classification;    Multi-label classification;    Monte Carlo methods;    Bayesian inference;   

DOI  :  10.1016/j.patcog.2013.10.006

来源: Elsevier

【 摘 要 】

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC 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, one of the most popular and highest-performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets. (C) 2013 Elsevier Ltd. All rights reserved.

【 授权许可】

Free