A Many-Objective Diversity-Guided Differential Evolution Algorithm for Multi-Label Feature Selection in High-Dimensional Datasets

Multi-label classification (MLC) is crucial as it allows for a more nuanced and realistic representation of complex real-world scenarios, where instances may belong to multiple categories simultaneously, providing a comprehensive understanding of the data. Effective feature selection in MLC is paramount as it cannot only enhance model efficiency and interpretability but also mitigate the curse of dimensionality, ensuring more accurate and streamlined predictions for complex, multi-label data. Despite the proven efficacy of evolutionary computation (EC) techniques in enhancing feature selection for multi-label datasets, research on feature selection in MLC remains sparse in the domain of multi- and many-objective optimization. This paper proposes a many-objective differential evolution algorithm called MODivDE for feature selection in high-dimensional MLC tasks. The MODivDE algorithm involves multiple improvements and innovations in quality indicator-based selection, logic-based search strategy, and diversity-based archive update. The results demonstrate the exceptional performance of the MODivDE algorithm across a diverse range of high-dimensional datasets, surpassing recently introduced many-objective and conventional multi-label feature selection algorithms. The advancements in MODivDE collectively contribute to significantly improved accuracy, efficiency, and interpretability compared to state-of-the-art methods in the realm of multi-label feature selection.