Quantum semi-supervised generative adversarial network for enhanced data classification

In this paper, we propose the quantum semi-supervised generative adversarial network (qSGAN). The system is composed of a quantum generator and a classical discriminator/classifier (D/C). The goal is to train both the generator and the D/C, so that the latter may get a high classification accuracy for a given dataset. Hence the qSGAN needs neither any data loading nor to generate a pure quantum state, implying that qSGAN is much easier to implement than many existing quantum algorithms. Also the generator can serve as a stronger adversary than a classical one thanks to its rich expressibility, and it is expected to be robust against noise. These advantages are demonstrated in a numerical simulation.

Automated summary

In this paper, a quantum semi-supervised generative adversarial network (qSGAN) is proposed, consisting of a quantum generator and a classical discriminator/classifier. The goal is to train both components to achieve high classification accuracy for a given dataset. qSGAN requires no data loading or generation of pure quantum states, making it easier to implement than existing quantum algorithms. The generator, with its rich expressibility, serves as a stronger adversary than a classical one and is expected to be robust against noise, as demonstrated in numerical simulations.