International Conference on Industrial Technology and Business Proceeding (INTECHBIZ)
The Role of Connectivity and Scale in Variational Quantum Classifiers (VQC): An Empirical Analysis of ZFeatureMap-EfficientSU2 on Standard Classification Datasets
This study presents a comparative empirical evaluation of Variational Quantum Classifier (VQC) performance within the Quantum Machine Learning (QML) framework, focusing on VQC architectural analysis under NISQ-era qubit constraints. The VQC was designed utilizing ZFeatureMap for data encoding and EfficientSU2 as the ansatz. A systematic test was performed to evaluate the impact of three entanglement topologies (default, circular, pairwise) and two qubit scales (4 and 8) with four classical optimizers on standard classification datasets: Iris, Wine, and Breast Cancer. The results demonstrated that no single configuration is universally optimal. The default topology achieved the highest peak accuracy on multi-class datasets (Iris: 97% with P-BFGS), suggesting its efficiency in simpler parameter landscapes. Conversely, the pairwise and circular topologies showed superior stability and competitive accuracy (up to 92%) on the high-dimensional Breast Cancer dataset, confirming that richer qubit connectivity is essential for effective feature separation in more complex classification problems. Increasing the scale from 4 to 8 qubits was found to be crucial for improving the overall stability and consistency of performance rather than merely increasing peak accuracy. These findings provide essential empirical guidance for designing optimal and trainable VQC architectures under current quantum device limitations.
This study presents a comparative empirical evaluation of Variational Quantum Classifier (VQC) performance within the Quantum Machine Learning (QML) framework, focusing on VQC architectural analysis under NISQ-era qubit constraints. The VQC was designed utilizing ZFeatureMap for data encoding and EfficientSU2 as the ansatz. A systematic test was performed to evaluate the impact of three entanglement topologies (default, circular, pairwise) and two qubit scales (4 and 8) with four classical optimizers on standard classification datasets: Iris, Wine, and Breast Cancer. The results demonstrated that no single configuration is universally optimal. The default topology achieved the highest peak accuracy on multi-class datasets (Iris: 97% with P-BFGS), suggesting its efficiency in simpler parameter landscapes. Conversely, the pairwise and circular topologies showed superior stability and competitive accuracy (up to 92%) on the high-dimensional Breast Cancer dataset, confirming that richer qubit connectivity is essential for effective feature separation in more complex classification problems. Increasing the scale from 4 to 8 qubits was found to be crucial for improving the overall stability and consistency of performance rather than merely increasing peak accuracy. These findings provide essential empirical guidance for designing optimal and trainable VQC architectures under current quantum device limitations.
This study looks at how the entangling structure of a variational quantum classifier (VQC) relates to its performance in breast cancer diagnosis, using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. We tested three three-qubit configurations that share the same EfficientSU2 ansatz, COBYLA optimizer, and stratified five-fold cross-validation, but differ in their entangling structure: a single- repetition Ising-type coupling (A), a two-repetition linear Ising-type coupling (B), and a fully connected Heisenberg-type coupling (C). Entanglement was measured with the von Neumann entropy and the Wootters concurrence. From A to C, the mean entropy rose from 0.40 to 0.71, accuracy rose from 92.98% to 93.68%, and F1-score rose from 90.32% to 91.28%. Configuration C was also the most stable across folds. However, the fold-level correlations between entanglement and performance were weak and not significant. Richer topologies also increase circuit expressivity, so the two effects cannot be fully separated. These results show an association, not a proven causal link, between entangling structure and VQC performance.
Early and accurate diagnosis of breast cancer plays a critical role in improving patient survival rates and reducing treatment costs. Classical machine learning algorithms such as Logistic Regression and Support Vector Machines (SVM) have demonstrated strong performance in medical diagnosis tasks; however, their scalability and representational limits motivate the exploration of emerging paradigms. Quantum Machine Learning (QML), particularly Variational Quantum Classifiers (VQC), has recently gained attention due to its potential to model complex decision boundaries using quantum circuits. This paper presents a comparative analysis between a Variational Quantum Classifier and classical machine learning models for binary breast cancer classification. The study employs dimensionality-reduced clinical data and evaluates model performance using accuracy, confusion matrices, decision boundary visualization, Principal Component Analysis (PCA), and Receiver Operating Characteristic (ROC) curves. Experimental results indicate that the VQC achieves competitive performance with classical approaches, demonstrating its feasibility for small-scale medical datasets and highlighting the promise of quantum-enhanced learning in healthcare applications.
Quantum Machine Learning (QML) is a newly emerging research area at the intersection of classical machine learning (CML) and quantum computing (QC). Data is becoming voluminous rapidly, so it is challenging for classical computers to train Machine Learning (ML) models over massive datasets. The hope is that quantum physics' intrinsic features, such as entanglement, superposition, and interference, could be exploited as resources for training ML models on big datasets that would otherwise be relatively impossible for classical computers. It is theoretically proven that quantum computers have an exponential-time advantage over their classical counterparts in solving several problems, e.g., complex large dimensional matrix multiplication, factorization problem, unstructured database search, etc. QML models attempt to find a quantum advantage over their classical counterparts. Variational Quantum Classifiers (VQC) are hybrid quantum neural networks to perform the task of classification using QML models. VQC models in the present NISQ (Noisy Intermediate Scale Quantum — 50 to 100 qubits) era can produce comparable and even better results than Classical models. In this article, we examined the performance of a VQC while performing a simple binary classification task. In this article, we use a VQC to evaluate this method's performance empirically. We constructed a VQC to predict the label of fresh input for the typical Iris dataset comprising pairings of target outputs and training inputs. Our quantum classifier can reasonably predict species labels using only four qubits. These levels are fairly good compared to the accuracy levels attained by classical classifiers.
Noisy Intermediate-Scale Quantum (NISQ) devices can be used to solve classification problems using a promising quantum machine learning technique called Variational Quantum Classifiers (VQC). The performance of VQCs is highly dependent on classical optimizers, and the understanding of the optimizer behavior within a given quantum architecture is limited. The proposed work is to present an Adaptive Optimizer-Enhanced Variational Quantum Classifier, which is a combination of a ZZFeatureMap for quantum data encoding and TwoLocal ansatz for variational learning, for solving non-linear binary classification problems. The proposed framework is tested using the Two Moons benchmark dataset, which is a popular benchmark for evaluating the ability of machine learning models to learn complex non-linear decision boundaries. The implementation is based on the Qiskit 1.2 and was run on a noiseless state vector simulator to remove the effects of hardware noise and focus on the effects of optimization. The three popular optimization techniques, namely ADAM, COBYLA and SPSA were explored under the same experimental setups. Besides the classification accuracy, a callback-based loss tracking mechanism was added to examine the speed of convergence, stability of optimization and evolution of losses during training. The experimental results showed that the overall accuracy of ADAM is 84.2%, which is the best, followed by COBYLA (79.3%) and SPSA (73.8%). Along with this, quantitative convergence analysis results showed that ADAM converged faster than the other optimizers and had lesser loss variance. It is shown that, with a proper optimization routine, a shallow two-qubit VQC can be used to successfully learn complex non-linear decision boundaries. The principal contribution of this work is a controlled optimizer-aware evaluation framework that integrates a fixed ZZFeatureMap–TwoLocal VQC architecture with callback-based convergence diagnostics to systematically analyse optimizer behaviour under identical experimental conditions.
The increasingly complex cybersecurity landscape requires more advanced network anomaly detection systems. Although, classical machine learning models are known to be effective, they reach computational bottlenecks when processing high-dimensional data. This study investigates the potential of Quantum Machine Learning (QML) for network traffic anomaly detection by evaluating four distinct Variational Quantum Classifier (VQC) architectures. A synthetic network traffic dataset is generated for the evaluations. The VQC models systematically varied feature encoding methods, parameterized ansatz circuits, quantum neural network types, and classical optimizers. Experimental results show that a trade-off exists between circuit expressivity and optimization stability. Deeper circuits (VQC-4) achieved higher accuracy of upto 89.0\%, while simultaneously being sensitive to training conditions. A shallower variant (VQC-1) under performed, although it had consistent and stable optimization curves. Class-dependent biases were also observed such as in VQC-2, where the model struggled to find an effective decision boundary, and produced a large number of false negatives. The best performing model in this study (VQC-3) combined ZFeatureMap with RealAmplitudes ansatz, optimized using ADAM. Comparative analysis against classical machine learning models such as Support Vector Machine and Random Forest reveal a performance gap, where classical models are able to achieve perfect classification performance on the synthetic data. It is concluded that classical algorithms remain dominant in their ability to classify structured data with relatively simple class separations. However, due to the observed potential of certain VQC configurations to learn decision boundaries to classify data, their utility for future applications in noisier, higher-dimensional problems is highlighted.
Variational Quantum Classifiers (VQCs) are a common class of hybrid quantum-classical models developed for nearterm quantum machine learning applications. Despite growing focus, it is still unclear how circuit design choices, particularly entanglement depth, affect learning performance and optimisation stability when compared to reliable classical baselines [1]. In this research, we provide a controlled empirical analysis of entanglement depth in VQCs for medical image classification utilizing pre-extracted deep feature representations. Under a predetermined experimental design, we assessed VQCs with no entanglement, single-layer entanglement, and two-layer interleaved entanglement with different training set sizes. Our findings demonstrate that in low-data regimes, increasing entanglement could negatively impact accuracy due to optimization instability [2] and may not always enhance performance. Since classical machine learning baselines consistently match or surpass quantum models, there is no performance advantage of variational quantum classifiers was observed under the evaluated experimental conditions and preprocessing constraints. These results emphasize the significance of thorough, comparative benchmarking for real-world use and draw attention to the expressivity optimization trade-offs inherent in variational quantum learning.