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.
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.
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.
One of the biggest obstacles to creating precise machine learning models is choosing representative and pertinent characteristics from big, unbalanced datasets. While too many features raise the risk of overfitting and computational expense, class imbalance frequently results in decreased accuracy and bias. The Simulated Annealing technique is used in this study to tackle a Quadratic Unconstrained Binary Optimization (QUBO) problem that is formulated as a quantum-assisted feature selection method to handle these problems. The technique seeks to reduce inter-feature redundancy and the number of selected features. There are 102,487 samples in the majority class and 11,239 in the minority class, totaling 28 characteristics in the experimental dataset. Nine ideal features were found during the feature selection method (12, 14, 15, 22, 23, 24, 25, 27, and 28). Ten-fold cross-validation was used to assess a Random Forest Classifier that was trained using an 80:20 split. With precision, recall, f1-score, and accuracy all hitting 1.00, the suggested QUBO+SMOTE method demonstrated exceptional performance. Comparatively, QUBO without SMOTE performed worse with accuracy 0.95 and minority-class f1-score of only 0.71, whereas a traditional Recursive Feature Elimination (RFE) approach obtained accuracy 0.97 with minority-class f1-score of 0.94. These findings indicate that QUBO can reduce dimensionality and address class imbalance which requires its integration with SMOTE. This study demonstrates how quantum computing can enhance the effectiveness and efficiency of machine learning, especially for large-scale imbalanced datasets
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.
Abstract In this study, the potential of quantum machine learning (QML) techniques based on trainable quantum circuits was explored for vector boson identification at the large hadron collider (LHC). Specifically, the compact muon solenoid (CMS) experiment dataset was employed to reconstruct the Z boson through the muon–antimuon ( μ+μ− μ + μ - ) decay channel using variational quantum circuits (VQC). To examine the effect of data structure on QML performance, various preprocessing strategies were applied, including different train/test splits, feature selection, dimensionality reduction, and class balancing techniques. The dataset was evaluated under two train/test configurations, namely a balanced split (70:30) and an imbalanced split (80:20), in order to examine the effect of class distribution on QML outcomes. Feature selection based on Random Forest (RF) was used to extract the most informative variables, while principal component analysis (PCA) was utilized to reduce input dimensionality and optimize qubit usage. To mitigate class imbalance, resampling techniques such as the Synthetic Minority Over-sampling Technique (SMOTE), SMOTE combined with edited nearest neighbors (SMOTEENN), and SMOTE with Tomek Links (SMOTETomek) were implemented. A comparative evaluation using stratified cross-validation was conducted to assess model performance and generalization ability across different configurations. The findings indicated that integrating PCA with resampling methods substantially improves the generalization capacity of the VQC model, especially in imbalanced settings. Among all configurations, SMOTE and SMOTEENN delivered the highest classification performance, boosting sensitivity to the minority class and enhancing model stability. These results highlight the significance of data structure, feature reduction, and resampling in classical quantum (CQ) data processing for high energy physics applications.
This work introduces a quantum K-Nearest Neighbor (K-NN) classifier algorithm. The algorithm utilizes angle encoding through a Quantum Random Access Memory (QRAM) using n number of qubit addresses with O(log(n)) space complexity. It incorporates Grover’s algorithm and the quantum SWAP-Test to identify similar states and determine the nearest neighbors with high probability, achieving Om search complexity, where m is the qubit address. We implement a simulation of the algorithm using IBM’s Qiskit with GPU support, applying it to the Iris and MNIST datasets with two different angle encodings. The experiments employ multiple QRAM cell sizes (8, 16, 32, 64, 128) and perform ten trials per size. According to the performance, accuracy values in the Iris dataset range from 89.3 ± 5.78% to 94.0 ± 1.56%. The MNIST dataset’s mean binary accuracy values range from 79.45 ± 18.84% to 94.00 ± 2.11% for classes 0 and 1. Additionally, a comparison of the results of this proposed approach with different state-of-the-art versions of QK-NN and the classical K-NN using Scikit-learn. This method achieves a 96.4 ± 2.22% accuracy in the Iris dataset. Finally, this proposal contributes an experimental result to the state of the art for the MNIST dataset, achieving an accuracy of 96.55 ± 2.00%. This work presents a new implementation proposal for QK-NN and conducts multiple experiments that yield more robust results than previous implementations. Although our average performance approaches still need to surpass the classic results, an experimental increase in the size of QRAM or the amount of data to encode is not achieved due to limitations. However, our results show promising improvement when considering working with more feature numbers and accommodating more data in the QRAM.
Class imbalance remains a major challenge in industrial condition monitoring and fault classification, where minority fault patterns can be poorly represented during machine learning. This work develops a noise-aware quantum-inspired oversampling framework and systematically evaluates its effectiveness and robustness for industrial and energy-system fault diagnosis. The principal artificial-intelligence contribution is a noise-aware extension of the Quantum Synthetic Minority Oversampling Technique (QSMOTE), in which quantum-inspired perturbations are introduced directly into the compact-swap-test-based similarity estimation used during synthetic minority-sample generation. Consequently, noise propagates through overlap estimation and angle computation to the generated samples, enabling direct assessment of the robustness of the oversampling mechanism rather than perturbing only the downstream classifier. The engineering application is evaluated on four public datasets covering solar-panel faults, bearing condition monitoring, engine failures, and industrial fault detection. Five classical classifiers are used to compare performance on the original imbalanced data, after QSMOTE-based balancing, and under noisy-QSMOTE. The results show substantial classifier-dependent benefits from QSMOTE, including improvements of up to 170% on the engine-failure dataset and accuracy exceeding 0.99 on the industrial fault-detection dataset. Robustness experiments across six quantum-inspired noise channels further demonstrate that perturbations in similarity estimation can produce markedly different downstream effects depending on the noise model and classifier. The proposed framework therefore provides a reproducible approach for jointly assessing class-imbalance mitigation and noise robustness of quantum-inspired oversampling in practical industrial artificial-intelligence applications.