Synthesizing realistic tabular data is challenging due to heterogeneous feature types and high dimensionality. We introduce QTabGAN, a hybrid quantum-classical generative adversarial framework for tabular data synthesis. QTabGAN is especially designed for settings where real data are scarce or restricted by privacy constraints. The model exploits the expressive power of quantum circuits to learn complex data distributions, which are then mapped to tabular features using classical neural networks. We evaluate QTabGAN on multiple classification and regression datasets and benchmark it against leading state-of-the-art generative models. Experiments show that QTabGAN achieves up to 54.07% improvement across various classification datasets and evaluation metrics, thus establishing a scalable quantum approach to tabular data synthesis and highlighting its potential for quantum-assisted generative modelling.
Synthesizing realistic tabular data is challenging due to heterogeneous feature types and high dimensionality. We introduce QTabGAN, a hybrid quantum-classical generative adversarial framework for tabular data synthesis. QTabGAN is especially designed for settings where real data are scarce or restricted by privacy constraints. The model exploits the expressive power of quantum circuits to learn complex data distributions, which are then mapped to tabular features using classical neural networks. We evaluate QTabGAN on multiple classification and regression datasets and benchmark it against leading state-of-the-art generative models. Experiments show that QTabGAN achieves up to 54.07% improvement across various classification datasets and evaluation metrics, thus establishing a scalable quantum approach to tabular data synthesis and highlighting its potential for quantum-assisted generative modelling.
In this paper, we introduce a novel quantum generative model for synthesizing tabular data. Synthetic data is valuable in scenarios where real-world data is scarce or private, as it can be used to augment or replace existing datasets. As enterprise data is predominantly tabular and heterogeneous, often consisting of both categorical and numerical features, this task is relevant across various industries such as healthcare, finance, and software. Existing quantum generative models are designed for homogeneous data; we seek to fill this gap by proposing a quantum generative adversarial network architecture with flexible data encoding and a novel quantum circuit ansatz for effectively modeling tabular data. The proposed approach is tested on the MIMIC-III healthcare and Adult Census datasets, with extensive benchmarking against leading classical models, CTGAN, CopulaGAN, VAE-GMM, and an LLM-based approach using the be-GReaT framework for tabular data synthesis. We evaluated our model as a proof-of-concept on reduced feature subsets using a noiseless statevector simulator on classical hardware. Our simulations show that, for the MIMIC-III dataset, our quantum model achieves competitive, and in some cases, leading performance with respect to an overall similarity score used in the open-source Python library SDMetrics. Additionally, we evaluate the generalization capabilities of the models using two custom-designed metrics that demonstrate the ability of the proposed quantum model to generate useful and novel tabular samples.
The need for synthetic medical data is growing rapidly as machine learning becomes more important in healthcare, especially with strict privacy rules like HIPAA in the United States and GDPR in Europe. While Generative Adversarial Networks (GANs) have shown potential in generating realistic synthetic data, they often face problems such as mode collapse, unstable training, and difficulty handling complex, high-dimensional medical datasets.In this work, we introduce a new Quantum Generative Adversarial Network (QUGAN) that combines the strengths of quantum and classical computing. The generator is built using a Variational Quantum Circuit (VQC), while the discriminator remains a classical neural network. To our knowledge, this is the first time a QUGAN has been applied to structured tabular healthcare data and especially using a VQC circuit in the generator, which makes up most real electronic health records but is rarely explored in quantum machine learning. The model was developed step by step, starting from a simple GAN baseline, and gradually improved into a more powerful hybrid system.The QUGAN performed considerably better compared with the standard baseline when tested on actual cardiovascular dataset. While achieving synthetic precision scores of up to 92%, it decreased the Maximum Mean Discrepancy (MMD) by 50.6%, the Kullback–Leibler (KL) divergence by 65.6%, and the Jensen–Shannon (JS) divergence by 67.7%. These results indicate that the model creates diverse samples close to real data, which are a key factor for safe data sharing and dependable analysis later. In short, our findings suggest that QUGANs that uses VQC circuits can be reliable method to produce tabular medical datasets.
Synthetic biological data play a crucial role in bioinformatics research, particularly in scenarios involving limited data availability and strict privacy constraints. However, conventional generative adversarial networks often face challenges in simultaneously preserving local statistical characteristics and global data distributions, motivating the exploration of quantum-enhanced generative models. This paper proposes and evaluates a hybrid quantum–classical generative adversarial network (QGAN) for efficient and high-quality biological data generation. The generator is implemented using a variational quantum circuit that encodes classical biological features into parameterized quantum states, while the discriminator is realized through a classical neural network architecture. The proposed framework is evaluated against classical GAN models using quantitative metrics, including the Classifier Two-Sample Test (C2ST), Maximum Mean Discrepancy (MMD) and Wasserstein Distance (WD). Experimental results show that the QGAN achieves stronger local statistical distribution matching, reflected by lower MMD values, whereas the Classical GAN demonstrates more stable global distribution alignment through lower WD. Furthermore, the analysis reveals that the stochastic sampling behavior of parameterized quantum circuits contributes to higher output variance during training, influencing large-scale distribution consistency. These findings indicate that hybrid quantum–classical generative models can effectively preserve localized statistical structures while highlighting the trade-off between local fidelity and global distribution stability, supporting their potential for future applications in genomics, drug discovery, and privacy-preserving biomedical data synthesis.
Abstract Data integrity and privacy are critical concerns in the financial sector. Traditional methods of data collection face challenges due to privacy regulations and time-consuming anonymization processes. In collaboration with Banco BV, we trained a hybrid quantum-classical generative adversarial network (HQGAN), where a quantum circuit serves as the generator and a classical neural network acts as the discriminator, to generate synthetic financial data efficiently and securely. We compared our proposed HQGAN model with a fully classical GAN by evaluating loss convergence and the MSE distance between the synthetic and real data. Although initially promising, our evaluation revealed that HQGAN failed to achieve the necessary accuracy to understand the intricate patterns in financial data. This outcome underscores the current limitations of quantum-inspired methods in handling the complexities of financial datasets. Graphical abstract
This paper investigates the application of Quantum Generative Adversarial Networks (QGANs) to data augmentation for machine learning. Traditional Generative Adversarial Networks (GANs) rely on classical neural networks, while this research explores leveraging quantum circuits as generators within a QGAN architecture. The core idea is to train a quantum generator to produce synthetic data samples, supplementing existing datasets with novel instances. The discriminator remains a classical neural network, tasked with distinguishing between real and generated data. We present a theoretical framework for this approach, outlining the mathematical formulation and key components. Specifically, we introduce the notation (x, s_1, s_2, ..., s_K) to represent data samples, generator states, and relevant parameters. The objective function for the QGAN is defined as minimizing the Jensen-Shannon divergence between the real and generated data distributions. The effectiveness of this approach is discussed, highlighting potential advantages and challenges. This work contributes to the emerging field of quantum machine learning and offers a novel strategy for improving the performance of machine learning models, particularly in scenarios with limited training data.
Credit card fraud detection is fundamentally challenged by extreme class imbalance, where fraudulent transactions are rare yet operationally critical. This imbalance often biases supervised learners toward the legitimate class, leading to high overall accuracy but weaker fraud-class recall and F1-score. This paper introduces Q-SYNTH, a hybrid classical--quantum generative adversarial framework in which a parameterized quantum circuit serves as the generator and a classical neural network serves as the discriminator. Q-SYNTH is designed for minority-class fraud synthesis in tabular data and is evaluated along two dimensions: statistical fidelity to real fraud samples and downstream performance for fraud detection. To this end, generated samples are assessed using distributional similarity measures based on Kolmogorov-Smirnov statistics and Wasserstein distances, real-vs-synthetic detectability measured by AUC-ROC, and downstream classification performance across both quantum and classical classifiers. Under the reported protocol, Q-SYNTH reduces marginal distribution mismatch relative to a classical GAN baseline while maintaining competitive downstream fraud-detection performance. Although SMOTE achieves the strongest feature-wise similarity and the classical GAN attains the highest downstream performance in several settings, Q-SYNTH offers a favorable compromise between distributional fidelity and downstream performance, supporting the feasibility of hybrid quantum augmentation for imbalanced fraud detection.