Abstract
In multi-label learning, instances can be associated with a set of class labels. The existing multi-label feature selection (MLFS) methods generally adopt either of these two strategies, namely, selecting a subset of features that is shared by all labels (common features) or exploring the most discriminative features for each label (label-specific features). However, both of them can play a key role in the discrimination of different labels. For example, common features can distinguish all labels, and label-specific features contribute to discriminating label's differences. They are important for the discriminability of selected features. On the other hand, it is well-known that exploiting label correlations can advance the performance of MLFS, and label correlations are local and only shared by a data subset in most cases. How to effectively learn and exploit local label correlations in the selection process is significant. In this paper, to address these problems, we propose a novel MLFS framework. Specially, common and label-specific features are simultaneously considered by introducing both $l_{2,1}$ -norm and $l_{1}$ -norm regularizers, local label correlations are automatically learned with probability and learned correlation information is efficiently exploited to help feature selection by constraining label correlations on the output of labels. A comparative study with seven state-of-the-art methods manifests the efficacy of our framework.
Highlights
Recent years have witnessed ever-growing applications involving multi-labeled data where instances can be associated with a set of class labels [1]–[3]
A typical characteristic among the existing multi-label feature selection (MLFS) methods is to select a subset of features that is shared by all labels, i.e., common features [10]–[12]
In light of the above observations, we propose a novel framework called ‘‘Common and Label-Specific Feature Selection using Local Label Correlations’’ (CLFS) which learns automatically and exploits effectively local correlations, and simultaneously consider common and labelspecific features
Summary
Recent years have witnessed ever-growing applications involving multi-labeled data where instances can be associated with a set of class labels [1]–[3]. Common features can distinguish all labels, and label-specific features contribute to discriminating label’s differences They are important for the discrimination of selected features. In light of the above observations, we propose a novel framework called ‘‘Common and Label-Specific Feature Selection using Local Label Correlations’’ (CLFS) which learns automatically and exploits effectively local correlations, and simultaneously consider common and labelspecific features. If we only force l2,1-norm on W, our model will obtain a weight matrix W with row sparsity, i.e. there are many zero rows in W, which imply these features are not correlated with all labels. We can obtain a weight matrix W where there are some non-zero elements even though most of elements in the same row are zero These non-zero values in W are expected to select label-specific features for the corresponding label. Common and label-specific features can be selected
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
