English

Improvement of Batch Normalization in Imbalanced Data

Machine Learning 2019-12-02 v1 Machine Learning

Abstract

In this study, we consider classification problems based on neural networks in data-imbalanced environment. Learning from an imbalanced data set is one of the most important and practical problems in the field of machine learning. A weighted loss function based on cost-sensitive approach is a well-known effective method for imbalanced data sets. We consider a combination of weighted loss function and batch normalization (BN) in this study. BN is a powerful standard technique in the recent developments in deep learning. A simple combination of both methods leads to a size-mismatch problem due to a mismatch between interpretations of effective size of data set in both methods. We propose a simple modification to BN to correct the size-mismatch and demonstrate that this modified BN is effective in data-imbalanced environment.

Keywords

Cite

@article{arxiv.1911.10687,
  title  = {Improvement of Batch Normalization in Imbalanced Data},
  author = {Muneki Yasuda and Seishirou Ueno},
  journal= {arXiv preprint arXiv:1911.10687},
  year   = {2019}
}
R2 v1 2026-06-23T12:25:51.198Z