Semisupervised Feature Selection With Multiscale Fuzzy Information Fusion: From Both Global and Local Perspectives

Abstract

In reality, the laborious nature of label annotation leads to the widespread existence of limited labeled data. Moreover, multiscale data have received widespread attention due to its rich knowledge representation. However, current research on multiscale data primarily focuses on supervised learning environments, while semisupervised feature selection for multiscale data with limited labels remains inadequately explored. Meanwhile, existing studies on multiscale data often emphasize selecting optimal scales and further conducting feature selection, but this strategy may result in losing potentially valuable information from other scales. To overcome these limitations, by adopting a multiscale fuzzy information fusion mechanism, this article proposes two new semisupervised feature selection approaches for multiscale data with limited labels from both global and local perspectives. Initially, by fusing fuzzy information at various scales, a label learning method is proposed to convert the decision of missing labels into a fuzzy decision of label distribution. Subsequently, label-distributed multiscale fuzzy global and local rough sets are constructed from global and local perspectives, respectively. Based on the two models, two semisupervised feature selection algorithms are developed based on global and local multiscale fuzzy information fusion. Experimental results demonstrate that, compared to other advanced feature selection algorithms, the two proposed algorithms can effectively handle multiscale data with limited labels and exhibit superior classification performance, computational efficiency, and robustness.