Approximating mutual information for multi-label feature selection

Jaesung Lee, Hyunki Lim, D.-W. Kim · Electronics Letters · 2012

Proposed is a new multi-label feature selection method that captures relationships between features and labels without transforming the problem into single-label classification. Using approximated joint mutual information, the proposed incremental feature selection algorithm provides markedly better classification performance than well-known conventional methods.

Read the paper · More papers on PaperTik