A Novel Feature Selection with Many-Objective Optimization and Learning Mechanism

Feature selection is extremely important in machine learning and data mining. Typical two-objective feature selection methods aim to minimize the number of features and maximize classification performance. However, they overlook the fact that there may be multiple subsets with similar information content for a given cardinality. The paper presents a many-objective feature selection approach to address this problem. Firstly, we establish a five-objective optimization model, which consists of classification accuracy, the number of features, feature relevance, feature redundancy, and feature complementarity. Therefore, the proposed model can enlarge the search space with more Pareto solutions. Secondly, we propose a wrapper structure for many-objective feature selection, which integrates a learning algorithm. Thirdly, in order to reduce the computional overhead, we propose a filter structure, which separates the learning algorithm. For implementation, we adopt NSGA-III multi-objective evolutionary algorithm and extreme learning machine. The experiments on mainstream datasets confirm the superiority of the proposed method.