A meta-learning imbalanced classification framework via boundary enhancement strategy with Bayes imbalance impact index.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

For imbalanced classification problem, algorithm-level methods can effectively avoid the information loss and noise introduction of data-level methods. However, the differences in the characteristics of the datasets, such as imbalance ratio, data dimension, and sample distribution, make it difficult to determine the optimal parameters of the algorithm-level methods, which leads to low universality. This paper proposes a meta-learning imbalanced classification framework via boundary enhancement strategy with Bayes imbalance impact index. First, the meta-learning idea is introduced to build multiple comprehensive training tasks. Each task contains a support set and a query set, which are randomly sampled from the original dataset. The support set is used to train the meta-classifier, and the meta-classifier's performance on the query set serves as an optimization object. This approach enables the meta-classifier to enhance itself based on the experiences gained from multiple training tasks, which makes it quickly adapt in the fine-tuning stage and exhibit excellent performance on the test set. Second, a boundary enhancement strategy with Bayes imbalance impact index (IBI3) is designed. The IBI3 value is used to identify boundary samples. On this basis, the feature interpolation among the boundary samples and their neighbor samples is applied to enhance the classification boundary, effectively alleviating the meta-classifier decision-making bias caused by data imbalance in the fine-tuning stage. Experimental results on 38 imbalanced public datasets with diverse characteristics show that the proposed method outperforms 24 typical imbalanced classification methods in F-measure and G-mean without parameters adjustment, which proves that the proposed method has greater universality.

Authors

  • Qiangwei Li
    School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China. Electronic address: 2782709791@bupt.edu.cn.
  • Xin Gao
    Department of Computer Science, New Jersey Institute of Technology, Newark, New Jersey, USA.
  • Heping Lu
    China Electric Power Research Institute Company Limited, Beijing, 100192, China. Electronic address: lhp@epri.sgcc.com.cn.
  • Baofeng Li
    China Electric Power Research Institute Company Limited, Beijing, 100192, China. Electronic address: libaofeng@epri.sgcc.com.cn.
  • Feng Zhai
    China Electric Power Research Institute Company Limited, Beijing, 100192, China; School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China. Electronic address: zhaifeng@epri.sgcc.com.cn.
  • Taizhi Wang
    School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China. Electronic address: wangtz@bupt.edu.cn.
  • Zhihang Meng
    School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China. Electronic address: mengzhihang@bupt.edu.cn.
  • Yu Hao
    School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China. Electronic address: haoyu2020@bupt.edu.cn.