Imbalanced Classification via Explicit Gradient Learning From Augmented Data

TL;DR

This paper introduces a deep meta-learning approach that augments imbalanced datasets with synthetic minority instances, explicitly learning their contributions to improve classification performance on imbalanced data.

Contribution

A novel deep meta-learning technique for dataset augmentation that explicitly learns the contribution of synthetic minority data in imbalanced classification.

Findings

Effective on synthetic datasets with various imbalance ratios

Improves minority class recognition without overfitting

Outperforms traditional re-sampling and re-weighting methods

Abstract

Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing approaches attempt to eliminate the bias through data re-sampling or re-weighting the loss in the learning process. Still, these methods tend to overfit the minority samples and perform poorly when the structure of the minority class is highly irregular. Here, we propose a novel deep meta-learning technique to augment a given imbalanced dataset with new minority instances. These additional data are incorporated in the classifier's deep-learning process, and their contributions are learned explicitly. The advantage of the proposed method is demonstrated on synthetic and real-world datasets with various imbalance ratios.