Quantum Generative Adversarial Networks

Haozhen Situ, Zhimin He, Yuyi Wang +2 more

Satya Prakash Yadav

Quantum computing and generative adversarial networks are combined into a single architecture, quantum generative adversarial networks (QGANs), a powerful tool for data generation data generation and simulation data simulation . Applications of QGANs QGAN applications , for example, finance and healthcare healthcare (including cryptography cryptography ), are repeated in this chapter. In this chapter, we will see how a QGAN approach to problems can preserve data privacy and explore more challenging features of machine learning or optimization in solving complex problem sets. We will give readers an idea of the many different applications these machines have and where they may fall short – not surprisingly, the author looks at a broad range of industries.

Xinghao Jia, Yi Zheng, Shuang Ren

Jincheng Zhang

This paper investigates the application of Quantum Generative Adversarial Networks (QGANs) for the generation of synthetic data. Traditional Generative Adversarial Networks (GANs) often face challenges in producing high-quality synthetic data, especially when dealing with complex data distributions. We propose a novel framework utilizing quantum circuits to construct both the generator and discriminator within a QGAN architecture. The core innovation lies in harnessing quantum superposition and interference during the adversarial training process to potentially improve the realism and diversity of the generated synthetic data. Our approach introduces a theoretical foundation and a conceptual design for QGANs, paving the way for future research and development in this emerging field. The primary goal is to demonstrate the potential benefits of incorporating quantum mechanical principles into the GAN framework, leading to enhanced synthetic data generation capabilities. The performance of a QGAN is expected to be superior to a classical GAN due to the unique properties of quantum systems.

Murphy Yuezhen Niu, Michael Broughton, Alexander Zlokapa +3 more

Yufan Cui, Han Qi, Hao Wang +2 more

With the wide application of 5G technology, the global Internet scale has grown sharply, putting forward higher requirements for both traditional network traffic prediction technology and network traffic prediction technology based on deep learning. Especially when dealing with large-scale data, the computational load and accuracy often fail to meet the actual demands. To overcome this problem, this paper introduces quantum technology and for the first time explores the challenge of applying quantum generative adversarial networks to network traffic prediction. Due to the advantage of efficient data processing capabilities of quantum generative adversarial networks (QGAN) and the sensitivity of long short-term memory networks (LSTM) to time series, the combination of the two provides a new research direction and application potential for time series analysis and prediction in the quantum field. This paper proposes a quantum generative adversarial network with an LSTM layer added to the generator. The temporal features extracted by LSTM are repeatedly embedded into the quantum circuit of the generator by using Angle encoding and data re-upload strategies. This enables quantum generative adversarial networks to handle temporal dependencies and enhances the expressive power of quantum circuits. Prediction experiments were conducted on the simulation platform using real network traffic data and compared with existing quantum neural network models for time series prediction such as QLSTM. The MAPE, $\mathbf{R}^{\mathbf{2}}$, MAE and RMSE indicators reached $3.4 \%, 98.6 \%, 0.018$ and 0.027 respectively, all showing significant advantages.