A Survey on Evolutionary Feature Selection in Multilabel Classification

Multilabel classification (MLC) involves assigning multiple labels to each instance from a predefined set of labels. With the increasing prevalence of multilabel datasets in real-world problems, MLC has become a popular area of research. These datasets frequently contain irrelevant, redundant, or noisy features, highlighting the importance of feature selection in MLC tasks. As a result, numerous multilabel feature selection (MLFS) approaches have been introduced in the literature. Given their effective search capabilities, evolutionary computation (EC) techniques have been adopted to develop MLFS approaches. However, there is a notable absence of a comprehensive survey dedicated to EC-based MLFS approaches to MLC tasks. Although few attempts have been made to address this gap, they do not provide detailed discussions on EC-based approaches. They also tend to overlook the strengths and weaknesses of existing approaches, especially regarding search, optimization, and evaluation processes. This article aims to fill this gap by presenting a comprehensive survey of EC-based MLFS approaches, focusing on the latest advancements, current challenges, and future directions. To be specific, we categorize EC-based MLFS approaches based on different criteria and provide detailed descriptions for each category.