Fast multi-label feature selection based on information-theoretic feature ranking

• A score function from mutual information between a feature and labels was derived.
• Unnecessary computations from the score function were discarded.
• A strategy to identify important labels from sparse label set was proposed.
• The computational cost of each component was analyzed theoretically.

Multi-label feature selection involves selecting important features from multi-label data sets. This can be achieved by ranking features based on their importance and then selecting the top-ranked features. Many multi-label feature selection methods for finding a feature subset that can improve multi-label learning accuracy have been proposed. In contrast, computationally efficient multi-label feature selection methods have not been studied extensively. In this study, we propose a fast multi-label feature selection method based on information-theoretic feature ranking. Experimental results demonstrate that the proposed method generates a feature subset significantly faster than several other multi-label feature selection methods for large multi-label data sets.