QuGAN: A Quantum State Fidelity based Generative Adversarial Network

Tremendous progress has been witnessed in artificial intelligence where neural network backed deep learning systems have been used, with applications in almost every domain. As a representative deep learning framework, Generative Adversarial Network (GAN) has been widely used for generating artificial images, text-to-image or image augmentation across areas of science, arts and video games. However, GANs are computationally expensive, sometimes computationally prohibitive. Furthermore, training GANs may suffer from convergence failure and modal collapse. Aiming at the acceleration of use cases for practical quantum computers, we propose QuGAN, a quantum GAN architecture that provides stable convergence, quantum-states based gradients and significantly reduced parameter sets. The QuGAN architecture runs both the discriminator and the generator purely on quantum state fidelity and utilizes the swap test on qubits to calculate the values of quantum-based loss functions. Built on quantum layers, QuGAN achieves similar performance with a 94.98% reduction on the parameter set when compared to classical GANs. With the same number of parameters, additionally, QuGAN outperforms state-of-the-art quantum based GANs in the literature providing a 48.33% improvement in system performance compared to others attaining less than 0.5% in terms of similarity between generated distributions and original data sets. QuGAN code is released at https://github.com/yingmao/Quantum-Generative-Adversarial-Network

[1]  Gavin E. Crooks,et al.  Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition , 2019, 1905.13311.

[2]  Masoud Mohseni,et al.  Learning to learn with quantum neural networks via classical neural networks , 2019, ArXiv.

[3]  John Preskill,et al.  Quantum Computing in the NISQ era and beyond , 2018, Quantum.

[4]  Gilles Brassard,et al.  Machine Learning in a Quantum World , 2006, Canadian AI.

[5]  Yi-Hsuan Yang,et al.  MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment , 2017, AAAI.

[6]  Qiang Guan,et al.  A Hybrid System for Learning Classical Data in Quantum States , 2020, 2021 IEEE International Performance, Computing, and Communications Conference (IPCCC).

[7]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Sebastian Nowozin,et al.  Stabilizing Training of Generative Adversarial Networks through Regularization , 2017, NIPS.

[9]  Shouvanik Chakrabarti,et al.  Quantum Wasserstein Generative Adversarial Networks , 2019, NeurIPS.

[10]  Yiyi Liao,et al.  Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[12]  Pekka Orponen,et al.  Computational complexity of neural networks: a survey , 1994 .

[13]  Ashish Kapoor,et al.  Quantum deep learning , 2014, Quantum Inf. Comput..

[14]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[15]  Prabhu Jayagopal,et al.  Generative adversarial networks: a survey on applications and challenges , 2020 .

[16]  Sirui Lu,et al.  Quantum Adversarial Machine Learning , 2020, ArXiv.

[17]  D. DiVincenzo.  Quantum gates and circuits , 1997, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[18]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[19]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[20]  Nathan Killoran,et al.  Quantum generative adversarial networks , 2018, Physical Review A.

[21]  Fang Zhao,et al.  Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis , 2017, NIPS.

[22]  Stefan Woerner,et al.  Quantum Generative Adversarial Networks for learning and loading random distributions , 2019, npj Quantum Information.

[23]  Peter Labus,et al.  Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues , 2020, VISIGRAPP.

[24]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[25]  Anmer Daskin.  Quantum Principal Component Analysis , 2015 .

[26]  David Von Dollen,et al.  TensorFlow Quantum: A Software Framework for Quantum Machine Learning , 2020, ArXiv.

[27]  Siddhant Garg,et al.  Advances in Quantum Deep Learning: An Overview , 2020, ArXiv.

[28]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[29]  Seth Lloyd,et al.  Quantum Generative Adversarial Learning. , 2018, Physical review letters.

[30]  Dacheng Tao,et al.  Experimental Quantum Generative Adversarial Networks for Image Generation , 2020, Physical Review Applied.

[31]  Shu-Hao Wu,et al.  Quantum generative adversarial learning in a superconducting quantum circuit , 2018, Science Advances.

[32]  Jinjun Xiong,et al.  Can Quantum Computers Learn Like Classical Computers? A Co-Design Framework for Machine Learning and Quantum Circuits , 2020, ArXiv.

[33]  Tomas E. Ward,et al.  Generative Adversarial Networks in Computer Vision , 2019, ACM Comput. Surv..

[34]  Tobias J. Osborne,et al.  Training deep quantum neural networks , 2020, Nature Communications.

[35]  Chao-Han Huck Yang,et al.  Variational Quantum Circuits for Deep Reinforcement Learning , 2019, IEEE Access.

[36]  Rishi Sharma,et al.  A Note on the Inception Score , 2018, ArXiv.

[37]  Cheng Xue,et al.  Effects of Quantum Noise on Quantum Approximate Optimization Algorithm , 2019 .

[38]  Travis S. Humble,et al.  Quantum supremacy using a programmable superconducting processor , 2019, Nature.