Adaptive Progressive Optimization Ensemble Approach for High-Dimensional Imbalanced Data Classification

Abstract

High-dimensional imbalanced data presents the problems of massive invalid features and class imbalance, making it arduous for classifiers to gain respectable outcomes. Compared to the individual classifier, classifier ensemble has great potential to elevate the performance. In this paper, an adaptive progressive optimization ensemble approach (APOEA) is designed for high-dimensional imbalanced data classification. First, a local subview optimization (LSO) is designed, it enables each ensemble member to focus on learning information from different local regions, which helps to achieve dimensionality reduction while maintaining diversity. Then, an adaptive critical subview optimization (ACSO) is developed for supplemental learning, which can adaptively identify the suitable critical regions and execute critical subview optimization. Finally, based on the critical subview, APOEA implements an over-sampling scheme to mitigate the effect of class imbalance for base classifier. Experimental results demonstrate that our APOEA outperforms other mainstream imbalanced learning algorithms.