Imbalanced datasets are a fundamental issue in industrial condition monitoring and fault classification pipelines, causing classical machine learning models to overfit the majority classes while failing to learn the minority fault patterns. This work presents a detailed benchmarking and robustness investigation of classical classifiers under class imbalance mitigation using the Quantum Synthetic Minority Oversampling Technique (QSMOTE) and quantum-inspired perturbations modelled using six noise channels. Four different datasets, the Solar Panel Image Dataset (SPID), the CWRU Bearing Dataset (CWRUBD), the Engine Failure Detection Dataset (EFDD), and the Industrial Fault Detection Dataset (IFDD), are tested across multi-class scenarios to determine the universality of these impacts. The results show that QSMOTE consistently corrects distributional skew and significantly enhances the performance of non-linear classifiers such as Random Forests (RF), Support Vector Machines (SVM), and Decision Trees (DT), yielding improvements of up to 170% on EFDD and achieving near-perfect accuracy ($\geq$0.99) on IFDD. Linear and probabilistic models, such as Linear Regression (LR) and Naive Bayes (NB), produce mixed results, with significant degradation in overlapping feature spaces due to interpolation-induced boundary distortion. A parallel robustness analysis under different noise models reveals that ensemble models (RF) and margin-based learners (SVM) maintain strong resilience, often preserving over 95% of baseline accuracy even under maximum noise. In contrast, NB and DT show substantial instability, especially on high-variance datasets. The findings establish a rigorous baseline for understanding how classical models behave under realistic imbalance and quantum-inspired noise.
Imbalanced datasets are a fundamental issue in industrial condition monitoring and fault classification pipelines, causing classical machine learning models to overfit the majority classes while failing to learn the minority fault patterns. This work presents a detailed benchmarking and robustness investigation of classical classifiers under class imbalance mitigation using the Quantum Synthetic Minority Oversampling Technique (QSMOTE) and quantum-inspired perturbations modelled using six noise channels. Four different datasets, the Solar Panel Image Dataset (SPID), the CWRU Bearing Dataset (CWRUBD), the Engine Failure Detection Dataset (EFDD), and the Industrial Fault Detection Dataset (IFDD), are tested across multi-class scenarios to determine the universality of these impacts. The results show that QSMOTE consistently corrects distributional skew and significantly enhances the performance of non-linear classifiers such as Random Forests (RF), Support Vector Machines (SVM), and Decision Trees (DT), yielding improvements of up to 170% on EFDD and achieving near-perfect accuracy (≥0.99) on IFDD. Linear and probabilistic models, such as Linear Regression (LR) and Naive Bayes (NB), produce mixed results, with significant degradation in overlapping feature spaces due to interpolation-induced boundary distortion. A parallel robustness analysis under different noise models reveals that ensemble models (RF) and margin-based learners (SVM) maintain strong resilience, often preserving over 95% of baseline accuracy even under maximum noise. In contrast, NB and DT show substantial instability, especially on high-variance datasets. The findings establish a rigorous baseline for understanding how classical models behave under realistic imbalance and quantum-inspired noise.
Abstract Quantum-inspired machine learning (QiML) employs mathematical principles from quantum theory, such as Hilbert-space representations and quantum state discrimination, to enhance classical learning algorithms. In this work, we investigate the integration of Quantum Synthetic Minority Oversampling Technique (QSMOTE) variants with two quantum-inspired classifiers: the Pretty Good Measurement (PGM) classifier and the kernelized Pretty Good Measurement (KPGM) classifier. We propose and analyze three QSMOTE variants, namely KNN-based, Fidelity-based, and Margin-based QSMOTE, designed to improve minority-class representation in imbalanced datasets through quantum-inspired similarity and sampling mechanisms. A unified theoretical and empirical comparison of PGM and KPGM is presented under amplitude and stereo encoding strategies with multiple quantum copies. Experimental evaluations on the Telco Customer Churn dataset demonstrate that the proposed quantum-inspired approaches consistently outperform a classical Random Forest baseline, particularly in terms of recall and balanced F1-score. Among all configurations, PGM with stereo encoding and ncopies=2 n copies = 2 achieves the best performance with an accuracy of 0.8512 and an F1-score of 0.8234, while KPGM exhibits competitive and more stable behavior across different QSMOTE variants, reaching accuracies of 0.8511 under stereo encoding and 0.8483 under amplitude encoding. The results further show that increasing the number of quantum copies systematically improves classification performance, especially for minority-class detection. This work highlights the effectiveness of combining quantum-inspired oversampling and classification strategies for imbalanced learning, while providing practical insights into the complementary strengths of measurement-based and kernel-based quantum-inspired machine learning frameworks.
Quantum-inspired machine learning (QiML) employs mathematical principles from quantum theory, such as Hilbert-space representations and quantum state discrimination, to enhance classical learning algorithms. In this work, we investigate the integration of Quantum Synthetic Minority Oversampling Technique (QSMOTE) variants with two quantum-inspired classifiers: the Pretty Good Measurement (PGM) classifier and the kernelized Pretty Good Measurement (KPGM) classifier. We propose and analyze three QSMOTE variants, namely KNN-based, Fidelity-based, and Margin-based QSMOTE, designed to improve minority-class representation in imbalanced datasets through quantum-inspired similarity and sampling mechanisms. A unified theoretical and empirical comparison of PGM and KPGM is presented under amplitude and stereo encoding strategies with multiple quantum copies. Experimental evaluations on the Telco Customer Churn dataset demonstrate that the proposed quantum-inspired approaches consistently outperform a classical Random Forest baseline, particularly in terms of recall and balanced F1-score. Among all configurations, PGM with stereo encoding and n_{copies}=2 achieves the best performance with an accuracy of 0.8512 and an F1-score of 0.8234, while KPGM exhibits competitive and more stable behavior across different QSMOTE variants, reaching accuracies of 0.8511 under stereo encoding and 0.8483 under amplitude encoding. The results further show that increasing the number of quantum copies systematically improves classification performance, especially for minority-class detection. This work highlights the effectiveness of combining quantum-inspired oversampling and classification strategies for imbalanced learning, while providing practical insights into the complementary strengths of measurement-based and kernel-based quantum-inspired machine learning frameworks.
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 TelecomChurn and evaluated alongside two prominent classification algorithms, Random Forest and Logistic Regression, to determine its impact along with varying proportions of synthetic data.
The class imbalance problem presents a critical challenge in real-world applications, particularly in high-stakes domains such as healthcare, finance, disaster management, and fault diagnosis, where accurate anomaly detection is paramount. Class imbalance often disrupts the inherent symmetry of data distributions, resulting in suboptimal performance of traditional machine learning models. Conventional approaches such as undersampling and oversampling are commonly employed to address this issue; however, these methods can introduce additional asymmetries, including information loss and overfitting, which ultimately compromise model efficacy. This study introduces an innovative approach leveraging quantum machine learning (QML), specifically the Variational Quantum Classifier (VQC), to restore and capitalize on the symmetrical properties of data distributions without relying on resampling techniques. By employing quantum circuits optimized to mitigate the asymmetries inherent in imbalanced datasets, the proposed method demonstrates consistently superior performance across diverse datasets, with notable improvements in Recall for minority classes. These findings underscore the potential of quantum machine learning as a robust alternative to classical methods, offering a symmetry-aware solution to class imbalance and advancing QML-driven technologies in fields where equitable representation and symmetry are of critical importance.
Imbalanced datasets in machine learning often result in biased models, particularly in classification problems when certain classes are under-represented. Traditional oversampling techniques like Synthetic Minority Over-sampling Technique (SMOTE), although popular, have difficulty producing synthetic samples of high quality when working in high-dimensional spaces or non-linear feature spaces. Existing techniques, such as SMOTE, do not fully account for the inherent complexity of non-linear structures of a minority class's distribution, which can produce negatively biased classifiers with poor generalization and the risk of overfitting to the minority class. This is further complicated by the reliance of traditional oversampling techniques on linear interpolation, which limits the possibilities of generating realistic or diverse and non-redundant synthetic samples. The proposed technique, QGOPQC, describes Quantum Generative Oversampling using Parameterized Quantum Circuits (PQCs). This approach describes using a quantum circuit, utilizing a novel implementation of a PQCs to overcome the non-linear problem. The development of synthetic samples of high fidelity using parameterized quantum circuits would better reflect the true data manifold of the generated class, allowing for a better learning process in a quantum training process, and using quantum state encoding, quantum circuit training, and classical optimization to produce diverse samples of synthetic classes while not compromising on information that maintains feature correlations. Demonstrated through a variety of results, the method achieved consistently higher AUC scores, reaching up to 0.92 compared to SMOTE’s 0.53, especially in high-dimensional scenarios. The proposed process of using QGOPQC has had a related beneficial effect on classifier performance when trained on imbalanced data, allowing for the process of generating non-redundant high-quality samples through a quantum method of sampling.
This paper introduces Quantum-SMOTEV2, an advanced variant of the Quantum-SMOTE method, leveraging quantum computing to address class imbalance in machine learning datasets without K-Means clustering. Quantum-SMOTEV2 synthesizes data samples using swap tests and quantum rotation centered around a single data centroid, concentrating on the angular distribution of minority data points and the concept of angular outliers (AOL). Experimental results show significant enhancements in model performance metrics at moderate SMOTE levels (30-36%), which previously required up to 50% with the original method. Quantum-SMOTEV2 maintains essential features of its predecessor (arXiv:2402.17398), such as rotation angle, minority percentage, and splitting factor, allowing for tailored adaptation to specific dataset needs. The method is scalable, utilizing compact swap tests and low depth quantum circuits to accommodate a large number of features. Evaluation on the public Cell-to-Cell Telecom dataset with Random Forest (RF), K-Nearest Neighbours (KNN) Classifier, and Neural Network (NN) illustrates that integrating Angular Outliers modestly boosts classification metrics like accuracy, F1 Score, AUC-ROC, and AUC-PR across different proportions of synthetic data, highlighting the effectiveness of Quantum-SMOTEV2 in enhancing model performance for edge cases.