Imbalanced Classification via Adversarial Minority Over-sampling

Jaehyung Kim, Jongheon Jeong, Jinwoo Shin

TL;DR: We develop a new method for imbalanced classification using adversarial examples

Abstract: In most real-world scenarios, training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue via synthesizing less-frequent classes with adversarial examples of other classes. Surprisingly, we found this counter-intuitive method can effectively learn generalizable features of minority classes by transferring and leveraging the diversity of the majority information. Our experimental results on various types of class-imbalanced datasets in image classification and natural language processing show that the proposed method not only improves the generalization of minority classes significantly compared to other re-sampling or re-weighting methods, but also surpasses other methods of state-of-art level for the class-imbalanced classification.

Keywords: imbalanced classification, adversarial examples