TabularQGAN: A quantum generative model for tabular data synthesis

The paper introduces TabularQGAN, a quantum generative adversarial network designed to synthesize tabular data with both categorical and numerical features. It proposes flexible data encoding and a novel quantum circuit ansatz, and evaluates the model on MIMIC‑III and Adult Census datasets, benchmarking against classical methods such as CTGAN, CopulaGAN, VAE‑GMM, and an LLM‑based approach. Results from noiseless statevector simulations show competitive or leading performance in overall similarity scores and demonstrate strong generalization through custom metrics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• benchmarks
• safety