Anomaly detection with variational quantum generative adversarial networks

Abstract

Generative adversarial networks (GANs) are a machine learning framework comprising a generative model for sampling from a target distribution and a discriminative model for evaluating the proximity of a sample to the target distribution. GANs exhibit strong performance in imaging or anomaly detection. However, they suffer from training instabilities, and sampling efficiency may be limited by the classical sampling procedure. We introduce variational quantum-classical Wasserstein GANs to address these issues and embed this model in a classical machine learning framework for anomaly detection. Classical Wasserstein GANs improve training stability by using a cost function better suited for gradient descent. Our model replaces the generator of Wasserstein GANs with a hybrid quantum-classical neural net and leaves the classical discriminative model unchanged. This way, high-dimensional classical data only enters the classical model and need not be prepared in a quantum circuit. We demonstrate the effectiveness of this method on a credit card fraud dataset. For this dataset our method shows performance on par with classical methods in terms of the $F_1$ score. We analyze the influence of the circuit ansatz, layer width and depth, neural net architecture parameter initialization strategy, and sampling noise on convergence and performance.

References in corpus (23)

• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Barren plateaus in quantum neural network training landscapes
• Quantum Circuit Learning
• Characterizing Quantum Supremacy in Near-Term Devices
• Parameterized quantum circuits as machine learning models
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• Quantum generative adversarial learning
• Quantum generative adversarial networks
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Continuous-variable quantum neural networks
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• The Expressive Power of Parameterized Quantum Circuits
• Average-case complexity versus approximate simulation of commuting quantum computations
• Quantum generative adversarial learning in a superconducting quantum circuit
• Quantum generative adversarial network for generating discrete distribution
• Quantum machine learning for quantum anomaly detection
• Learning and Inference on Generative Adversarial Quantum Circuits
• The Quantum Wasserstein Distance of Order 1
• On the Quantum versus Classical Learnability of Discrete Distributions
• Quantum Anomaly Detection with Density Estimation and Multivariate Gaussian Distribution
• Near-Term Quantum-Classical Associative Adversarial Networks

Cited by in corpus (19)

• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Mixed Quantum-Classical Method For Fraud Detection with Quantum Feature Selection
• Quantum Machine Learning: from physics to software engineering
• Variational inference with a quantum computer
• Quantum Machine Learning for Finance
• Quantum semi-supervised generative adversarial network for enhanced data classification
• AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Images
• QFNN-FFD: Quantum Federated Neural Network for Financial Fraud Detection
• Improving the speed of variational quantum algorithms for quantum error correction
• Quantum Generative Adversarial Networks in a Silicon Photonic Chip with Maximum Expressibility
• Quantum continual learning of quantum data realizing knowledge backward transfer
• The Wasserstein distance of order 1 for quantum spin systems on infinite lattices
• Accelerating the drive towards energy-efficient generative AI with quantum computing algorithms
• Energy risk analysis with Dynamic Amplitude Estimation and Piecewise Approximate Quantum Compiling
• Quantum density estimation with density matrices: Application to quantum anomaly detection
• Quantum generative modeling for financial time series with temporal correlations
• Quantum Anomaly Detection with a Spin Processor in Diamond
• Exploring exotic configurations with anomalous features using deep learning: Application of classical and quantum-classical hybrid anomaly detection
• Critical Scaling of the Quantum Wasserstein Distance