Experimental Quantum Generative Adversarial Networks for Image Generation

Abstract

Quantum machine learning is expected to be one of the first practical applications of near-term quantum devices. Pioneer theoretical works suggest that quantum generative adversarial networks (GANs) may exhibit a potential exponential advantage over classical GANs, thus attracting widespread attention. However, it remains elusive whether quantum GANs implemented on near-term quantum devices can actually solve real-world learning tasks. Here, we devise a flexible quantum GAN scheme to narrow this knowledge gap, which could accomplish image generation with arbitrarily high-dimensional features, and could also take advantage of quantum superposition to train multiple examples in parallel. For the first time, we experimentally achieve the learning and generation of real-world hand-written digit images on a superconducting quantum processor. Moreover, we utilize a gray-scale bar dataset to exhibit the competitive performance between quantum GANs and the classical GANs based on multilayer perceptron and convolutional neural network architectures, respectively, benchmarked by the Fréchet Distance score. Our work provides guidance for developing advanced quantum generative models on near-term quantum devices and opens up an avenue for exploring quantum advantages in various GAN-related learning tasks.

arXiv commentThis work was completed in 2019, and the first version of manuscript was submitted to the journal in January 2020

References in corpus (35)

• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Quantum computational advantage using photons
• The theory of variational hybrid quantum-classical algorithms
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Quantum principal component analysis
• Parameterized quantum circuits as machine learning models
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Quantum generative adversarial learning
• Quantum generative adversarial networks
• Quantum advantage with shallow circuits
• Perceptual Adversarial Networks for Image-to-Image Transformation
• Quantum Circuits for General Multiqubit Gates
• Superconducting Quantum Computing: A Review
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Quantum-state preparation with universal gate decompositions
• The Expressive Power of Parameterized Quantum Circuits
• Towards Quantum Machine Learning with Tensor Networks
• Hybrid Quantum-Classical Convolutional Neural Networks
• Differentiable Learning of Quantum Circuit Born Machine
• Quantum generalisation of feedforward neural networks
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Soundness and completeness of quantum root-mean-square errors
• Efficient decomposition of quantum gates
• Entanglement-Based Machine Learning on a Quantum Computer
• Stochastic gradient descent for hybrid quantum-classical optimization
• Noise Resilience of Variational Quantum Compiling
• Quantum generative adversarial learning in a superconducting quantum circuit
• Adequacy of Si:P Chains as Fermi-Hubbard Simulators
• Demonstration of Topological Data Analysis on a Quantum Processor

Cited by in corpus (66)

• Realization of an Error-Correcting Surface Code with Superconducting Qubits
• Quantum circuit architecture search for variational quantum algorithms
• Quantum machine learning for image classification
• Efficient measure for the expressivity of variational quantum algorithms
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Quantum Machine Learning: from physics to software engineering
• Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
• Towards understanding the power of quantum kernels in the NISQ era
• Recent advances for quantum classifiers
• Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry
• Variational Quantum Algorithm for Estimating the Quantum Fisher Information
• Generative quantum machine learning via denoising diffusion probabilistic models
• Hybrid quantum-classical machine learning for generative chemistry and drug design
• Generalized quantum circuit differentiation rules
• Realizing a quantum generative adversarial network using a programmable superconducting processor
• Quantum Kernel Methods for Solving Differential Equations
• Generative Quantum Learning of Joint Probability Distribution Functions
• Quantum Neuronal Sensing of Quantum Many-Body States on a 61-Qubit Programmable Superconducting Processor
• A Variational Quantum Attack for AES-like Symmetric Cryptography
• Simulating Noisy Variational Quantum Algorithms: A Polynomial Approach
• A performance characterization of quantum generative models
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• Quantum Natural Language Processing
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• Quantum algorithm for credit valuation adjustments
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• Quantum Generative Learning for High-Resolution Medical Image Generation
• Quantum Optimization for Training Quantum Neural Networks
• The quantum cost function concentration dependency on the parametrization expressivity
• Efficient option pricing with unary-based photonic computing chip and generative adversarial learning
• Quantum Latent Diffusion Models
• Cryogenic Multiplexing Control Chip for Superconducting Quantum Processor
• Quantum gradient descent algorithms for nonequilibrium steady states and linear algebraic systems
• Introducing Non-Linear Activations into Quantum Generative Models
• Variational quantum state discriminator for supervised machine learning
• Towards Efficient Quantum Hybrid Diffusion Models
• Noise-Resistant Quantum State Compression Readout
• Hybrid quantum learning with data re-uploading on a small-scale superconducting quantum simulator
• Quantum autoencoders for image classification
• Parameterized quantum circuits as universal generative models for continuous multivariate distributions
• Protocols for classically training quantum generative models on probability distributions
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Quantum generative adversarial learning in photonics
• Evaluating the Resilience of Variational Quantum Algorithms to Leakage Noise
• Protocols for Trainable and Differentiable Quantum Generative Modelling
• Quantum Generative Adversarial Networks in a Silicon Photonic Chip with Maximum Expressibility
• Photonic quantum generative adversarial networks for classical data
• An RNN-policy gradient approach for quantum architecture search
• Parameter-Parallel Distributed Variational Quantum Algorithm
• Towards AutoQML: A Cloud-Based Automated Circuit Architecture Search Framework
• Quantum neural compressive sensing for ghost imaging
• Classification and reconstruction for single-pixel imaging with classical and quantum neural networks
• Generative Invertible Quantum Neural Networks
• Enhancing Variational Quantum Circuit Training: An Improved Neural Network Approach for Barren Plateau Mitigation
• Quantum Inception Score
• Multiqubit state learning with entangling quantum generative adversarial networks
• Quantum Anomaly Detection with a Spin Processor in Diamond
• Quantum generative modeling for financial time series with temporal correlations
• GAN decoder on a quantum toric code for noise-robust quantum teleportation
• ReCon: Reconfiguring Analog Rydberg Atom Quantum Computers for Quantum Generative Adversarial Networks
• Quantum generative model on bicycle-sharing system and an application
• Quantum Noise Sensing by generating Fake Noise
• Quantum-assisted tracer dispersion in turbulent shear flow
• Verifying Adversarial Robustness in Quantum Machine Learning: from theory to physical validation via a software tool
• Variational Quantum Generative Modeling by Sampling Expectation Values of Tunable Observables
• Quantum Chebyshev Probabilistic Models for Fragmentation Functions