A Quantum Approach to Synthetic Minority Oversampling Technique (SMOTE)

TL;DR

This paper introduces Quantum-SMOTE, a quantum computing-based method for generating synthetic minority class data to address class imbalance in machine learning, offering more control and scalability over traditional SMOTE.

Contribution

It presents a novel quantum algorithm for oversampling minority classes, diverging from conventional neighbor-based methods, and demonstrates its application on real datasets with flexible hyperparameters.

Findings

Quantum-SMOTE effectively balances classes in datasets.

The method improves classifier performance on imbalanced data.

It scales well with high-dimensional feature spaces.

Abstract

The paper proposes the Quantum-SMOTE method, a novel solution that uses quantum computing techniques to solve the prevalent problem of class imbalance in machine learning datasets. Quantum-SMOTE, inspired by the Synthetic Minority Oversampling Technique (SMOTE), generates synthetic data points using quantum processes such as swap tests and quantum rotation. The process varies from the conventional SMOTE algorithm's usage of K-Nearest Neighbors (KNN) and Euclidean distances, enabling synthetic instances to be generated from minority class data points without relying on neighbor proximity. The algorithm asserts greater control over the synthetic data generation process by introducing hyperparameters such as rotation angle, minority percentage, and splitting factor, which allow for customization to specific dataset requirements. Due to the use of a compact swap test, the algorithm can accommodate a large number of features. Furthermore, the approach is tested on a public dataset of Telecom Churn and evaluated alongside two prominent classification algorithms, Random Forest and Logistic Regression, to determine its impact along with varying proportions of synthetic data.