Deep Synthetic Minority Over-Sampling Technique

TL;DR

This paper introduces Deep SMOTE, a deep learning-based extension of SMOTE, which stabilizes synthetic data generation and improves classification performance on imbalanced datasets.

Contribution

It proposes a novel deep neural network regression approach to enhance SMOTE, reducing variability and improving accuracy in imbalanced classification tasks.

Findings

Deep SMOTE outperforms traditional SMOTE in precision, F1 score, and AUC.

The method stabilizes synthetic data generation across multiple runs.

Experimental results demonstrate improved classification results.

Abstract

Synthetic Minority Over-sampling Technique (SMOTE) is the most popular over-sampling method. However, its random nature makes the synthesized data and even imbalanced classification results unstable. It means that in case of running SMOTE n different times, n different synthesized in-stances are obtained with n different classification results. To address this problem, we adapt the SMOTE idea in deep learning architecture. In this method, a deep neural network regression model is used to train the inputs and outputs of traditional SMOTE. Inputs of the proposed deep regression model are two randomly chosen data points which are concatenated to form a double size vector. The outputs of this model are corresponding randomly interpolated data points between two randomly chosen vectors with original dimension. The experimental results show that, Deep SMOTE can outperform traditional SMOTE in terms of precision, F1 score and Area Under Curve (AUC) in majority of test cases.