Feature selection for multi-label classification problems

Authors:
Gauthier Doquire;Michel Verleysen
Affiliations:
Université catholique de Louvain, Machine Learning Group - ICTEAM, Louvain-la-Neuve, Belgium;Université catholique de Louvain, Machine Learning Group - ICTEAM, Louvain-la-Neuve, Belgium
Venue:
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part I
Year:
2011

Citing 6
Cited 6

BoosTexter: A Boosting-based Systemfor Text Categorization

Machine Learning - Special issue on information retrieval
An introduction to variable and feature selection

The Journal of Machine Learning Research
Resampling methods for parameter-free and robust feature selection with mutual information

Neurocomputing
ML-KNN: A lazy learning approach to multi-label learning

Pattern Recognition
Information-theoretic feature selection for functional data classification

Neurocomputing
Protein classification with multiple algorithms

PCI'05 Proceedings of the 10th Panhellenic conference on Advances in Informatics

Feature selection for multi-label classification using multivariate mutual information

Pattern Recognition Letters
Filter approach feature selection methods to support multi-label learning based on relieff and information gain

SBIA'12 Proceedings of the 21st Brazilian conference on Advances in Artificial Intelligence
A Comparison of Multi-label Feature Selection Methods using the Problem Transformation Approach

Electronic Notes in Theoretical Computer Science (ENTCS)
Letters: Mutual information-based feature selection for multilabel classification

Neurocomputing
Hierarchical multi-label classification using local neural networks

Journal of Computer and System Sciences
Multi-label learning under feature extraction budgets

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes the use of mutual information for feature selection in multi-label classification, a surprisingly almost not studied problem. A pruned problem transformation method is first applied, transforming the multi-label problem into a single-label one. A greedy feature selection procedure based on multidimensional mutual information is then conducted. Results on three databases clearly demonstrate the interest of the approach which allows one to sharply reduce the dimension of the problem and to enhance the performance of classifiers.