基于量子生成对抗网络的数据重构

doi:10.3778/j.issn.1002-8331.2211-0363

摘要/Abstract

摘要： 使用神经网络实现数据重构是人工智能领域一项十分重要的研究课题。生成对抗网络（generative adversarial network，GAN）作为近年来人工智能的热门算法，在完成数据重构任务中有较好的表现。量子计算作为一种能够加速经典计算的新型计算模式，正不断地与经典人工智能算法相融合。其中，量子生成对抗网络（quantum generative adversarial network，QGAN）在图像相关任务中具有良好的表现，但是量子模型的拟合能力还有待提高。故此，提出了一种基于GAN框架的量子-经典混合生成对抗网络（Q-CGAN）用于实现数据重构任务。该框架利用经典网络的非线性提高拟合效果，利用量子特性提供量子加速。使用MNIST手写数据集对比验证了量子模型和混合模型的重构效果，结果显示，Q-CGAN较纯量子生成器在数据重构过程中具有更好的表现。此外，还研究了混合模型中使用不同量子编码方案和不同参数化量子线路对数据重构效果的影响。

关键词: 量子计算, 混合生成对抗网络, 数据重构

Abstract: Data reconstruction using neural networks is a very important research topic in the field of artificial intelligence. Generative adversarial network (GAN), as a popular algorithm of artificial intelligence in recent years, has a good performance in completing data reconstruction tasks. As a new computing mode that can accelerate classical computing, quantum computing is constantly merging with classical artificial intelligence algorithms. Among them, pure quantum generative adversarial network (QGAN) has a good performance in image related tasks. However, since the fitting ability in the quantum model still needs to be improved, this paper proposes a hybrid generative confrontation network (Q-CGAN) based on the GAN framework to realize the data reconstruction task. The framework exploits classical nonlinearities to improve fitting performance and quantum properties to provide quantum speedups. Using the MNIST handwritten data set to compare and verify the reconstruction effect of the hybrid model in this network, the results show that Q-CGAN has better performance in the data reconstruction process than pure quantum generators. In addition, the effect of using different quantum encoding schemes and different parameterized quantum circuits in the hybrid model on the data reconstruction effect is also studied.

Key words: quantum computing, hybrid generative adversarial network, data reconstruction

江奕达, 王明明. 基于量子生成对抗网络的数据重构[J]. 计算机工程与应用, 2024, 60(5): 156-164.

JIANG Yida, WANG Mingming. Data Reconstruction Based on Quantum Generative Adversarial Networks[J]. Computer Engineering and Applications, 2024, 60(5): 156-164.

参考文献

[1] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[2] HAN C, HAYASHI H, RUNDO L, et al. GAN-based synthetic brain MR image generation[C]//2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018: 734-738.
[3] YU X, QU Y, HONG M. Underwater-GAN: underwater image restoration via conditional generative adversarial network[C]//Proceedings of the International Conference on Pattern Recognition, 2018: 66-75.
[4] CHEREPKOV A, VOYNOV A, BABENKO A. Navigating the GAN parameter space for semantic image editing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 3671-3680.
[5] LIU R, WANG X, LU H, et al. SCCGAN: style and characters inpainting based on CGAN[J]. Mobile networks and applications, 2021, 26(1): 3-12.
[6] ZHU Y, ZHANG Y, YANG H, et al. GANCoder: an automatic natural language-to-programming language translation approach based on GAN[C]//CCF International Conference on Natural Language Processing and Chinese Computing, 2019: 529-539.
[7] 张帅勇, 刘美琴, 姚超, 等. 分级特征反馈融合的深度图像超分辨率重建[J]. 自动化学报. 2022, 48(4): 992-1003.
ZHANG S Y, LIU M Q, YAO C, et al. Hierarchical feature feedback network for depth super-resolution reconstruction[J]. Acta Automatica Sinica, 2022, 48(4): 992-1003.
[8] 杨才东, 李承阳, 李忠博, 等. 深度学习的图像超分辨率重建技术综述[J]. 计算机科学与探索, 2022, 16(9): 1990-2010.
YANG C D, LI C Y, LI Z B, et al. Review of image super-resolution reconstruction algorithms based on deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(9): 1990-2010.
[9] 钟梦圆, 姜麟. 超分辨率图像重建算法综述[J]. 计算机科学与探索, 2022, 16(5): 972-990.
ZHONG M Y, JIANG L. Review of super-resolution image reconstruction algorithms[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(5): 972-990.
[10] DONG C, LOY C C, HE K, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(2): 295-307.
[11] DONG C, LOY C C, TANG X. Accelerating the super-resolution convolutional neural network[C]//Proceedings of the European Conference on Computer Vision, 2016: 391-407.
[12] SHI W, CABALLERO J, HUSZáR F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 1874-1883.
[13] KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 1646-1654.
[14] LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017: 136-144.
[15] YANG F, YANG H, FU J, et al. Learning texture transformer network for image super-resolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 5791-5800.
[16] LIU C, LI H, LIANG Z, et al. A novel deep-learning-based enhanced texture transformer network for reference image super-resolution[J]. Electronics, 2022, 11(19): 3038.
[17] XIE W, HUANG T, WANG M. MNSRNet: multimodal transformer network for 3D surface super-resolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 12703-12712.
[18] LEDIG C, THEIS L, HUSZáR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4681-4690.
[19] SHOR P W. Algorithms for quantum computation: discrete logarithms and factoring[C]//Proceedings of the 35th Annual Symposium on Foundations of Computer Science, 1994: 124-134.
[20] JOZSA R. Searching in Grover’s algorithm[J]. arXiv:quantum-physics/9901021,1999.
[21] ZHANG M, DONG L, ZENG Y, et al. Improved circuit implementation of the HHL algorithm and its simulations on QISKIT[J]. Scientific Reports, 2022, 12(1): 1-12.
[22] AHMED S. Pattern recognition with quantum support vector machine (QSVM) on near term quantum processors[D]. Dhaka: Brac University, 2019.
[23] LLOYD S, MOHSENI M, REBENTROST P. Quantum principal component analysis[J]. Nature Physics, 2014, 10(9): 631-633.
[24] AMIN M H, ANDRIYASH E, ROLFE J, et al. Quantum Boltzmann machine[J]. Physical Review X, 2018, 8(2): 21050.
[25] A?MEUR E, BRASSARD G, GAMBS S. Quantum clustering algorithms[C]//Proceedings of the 24th International Conference on Machine Learning, 2007: 1-8.
[26] BIAMONTE J, WITTEK P, PANCOTTI N, et al. Quantum machine learning[J]. Nature, 2017, 549: 195-202.
[27] BENEDETTI M, LLOYD E, SACK S, et al. Parameterized quantum circuits as machine learning models[J]. Quantum Science and Technology, 2019, 4(4): 43001.
[28] PRESKILL J. Quantum computing in the NISQ era and beyond[J]. arXiv:1801.00862,2018.
[29] KERENIDIS I, LANDMAN J, PRAKASH A. Quantum algorithms for deep convolutional neural networks[J]. arXiv:1911.01117,2019.
[30] PANDIAN A, KANCHANADEVI K, MOHAN V C, et al. Quantum generative adversarial network and quantum neural network for image classification[C]//2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), 2022: 473-478.
[31] DONG D, CHEN C, LI H, et al. Quantum reinforcement learning[J]. IEEE Transactions on Systems, Man, and Cybernetics (Part B), 2008, 38(5): 1207-1220.
[32] HUR T, KIM L, PARK D K. Quantum convolutional neural network for classical data classification[J]. Quantum Machine Intelligence, 2022, 4(1): 1-18.
[33] HUANG H, DU Y, GONG M, et al. Experimental quantum generative adversarial networks for image generation[J]. Physical Review Applied, 2021, 16(2): 24051.
[34] YAN F, VENEGAS-ANDRACA S E, HIROTA K. Toward implementing efficient image processing algorithms on quantum computers[J]. Soft Computing, 2022: 1-13.
[35] WANG Z, XU M, ZHANG Y. Review of quantum image processing[J]. Archives of Computational Methods in Engineering, 2022, 29(2): 737-761.
[36] LIU Z W, WANG L, CUI M. Quantum image segmentation based on grayscale morphology[J]. IEEE Transactions on Quantum Engineering, 2022, 3: 1-12.
[37] YAN F, ZHAO S, VENEGAS-ANDRACA S E, et al. Implementing bilinear interpolation with quantum images[J]. Digital Signal Processing, 2021, 117: 103149.
[38] NIU M Y, ZLOKAPA A, BROUGHTON M, et al. Entangling quantum generative adversarial networks[J]. Physical Review Letters, 2022, 128(22): 220505.
[39] STEIN S A, BAHERI B, CHEN D, et al. QuGAN: a generative adversarial network through quantum states[J]. arXiv:2010.09036,2020.
[40] RUDOLPH M S, TOUSSAINT N B, KATABARWA A, et al. Generation of high-resolution handwritten digits with an ion-trap quantum computer[J]. Physical Review X, 2022, 12(3): 31010.
[41] WANG M, JIANG Y. Data reconstruction based on quantum neural networks[J]. arXiv:2209.05711,2022.
[42] WU C, QI B, CHEN C, ET AL. Robust learning control design for quantum unitary transformations[J]. IEEE Transactions on Cybernetics, 2016, 47(12): 4405-4417.
[43] SIM S, JOHNSON P D, ASPURU GUZIK A. Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms[J]. Advanced Quantum Technologies, 2019, 2(12): 1900070.
[44] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[45] ZHOU N, ZHANG T, XIE X, et al. Hybrid quantum-classical generative adversarial networks for image generation via learning discrete distribution[J]. Signal Processing: Image Communication, 2022: 116891.
[46] LI J, LI B, XU J, et al. Fully connected network-based intra prediction for image coding[J]. IEEE Transactions on Image Processing, 2018, 27(7): 3236-3247.
[47] LIU J, LIM K H, WOOD K L, et al. Hybrid quantum-classical convolutional neural networks[J]. Science China Physics, Mechanics & Astronomy, 2021, 64(9): 1-8.
[48] NGUEMTO S, LEYTON-ORTEGA V. Re-QGAN: an optimized adversarial quantum circuit learning framework[J]. arXiv:2208.02165,2022.