Online multi-label streaming feature selection based on neighborhood rough set with label correlation

Online multi-label streaming feature selection has gained significant interest in high-volume data applications. Neighborhood Rough Set (NRS) has emerged as a practical tool for handling multi-label feature selection. However, the majority of existing works have been concentrated on situations where labels are treated as independent and unrelated entities, disregarding the genuine context of interdependence and correlation among labels. To address this issue, this paper introduces a novel approach for online multi-label streaming feature selection, incorporating NRS and Label Correlation (LC). In our approach, we propose the concept of strongly related label subsets based on NRS. As considering label correlation, we compute the similarity between different labels and assign different weights to each label. This integrated method enhances the effectiveness of feature selection by leveraging the interdependencies among labels. he proposed reliability of the algorithm is validated experimentally.