Hybrid Quantum-Classical Graph Convolutional Network

Abstract

The high energy physics (HEP) community has a long history of dealing with large-scale datasets. To manage such voluminous data, classical machine learning and deep learning techniques have been employed to accelerate physics discovery. Recent advances in quantum machine learning (QML) have indicated the potential of applying these techniques in HEP. However, there are only limited results in QML applications currently available. In particular, the challenge of processing sparse data, common in HEP datasets, has not been extensively studied in QML models. This research provides a hybrid quantum-classical graph convolutional network (QGCNN) for learning HEP data. The proposed framework demonstrates an advantage over classical multilayer perceptron and convolutional neural networks in the aspect of number of parameters. Moreover, in terms of testing accuracy, the QGCNN shows comparable performance to a quantum convolutional neural network on the same HEP dataset while requiring less than $50\%$ of the parameters. Based on numerical simulation results, studying the application of graph convolutional operations and other QML models may prove promising in advancing HEP research and other scientific fields.

References in corpus (35)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Quantum Computing in the NISQ era and beyond
• Semi-Supervised Classification with Graph Convolutional Networks
• An overview of gradient descent optimization algorithms
• A variational eigenvalue solver on a quantum processor
• Quantum Mechanics helps in searching for a needle in a haystack
• Quantum Circuit Learning
• Graph Neural Networks: A Review of Methods and Applications
• Deep Convolutional Networks on Graph-Structured Data
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Graph Convolutional Matrix Completion
• Evaluating analytic gradients on quantum hardware
• Circuit-centric quantum classifiers
• Quantum Computational Supremacy
• Interaction Networks for Learning about Objects, Relations and Physics
• Quantum generative adversarial networks
• Transfer learning in hybrid classical-quantum neural networks
• Deep Learning and its Application to LHC Physics
• Qulacs: a fast and versatile quantum circuit simulator for research purpose
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• A Convolutional Neural Network Neutrino Event Classifier
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Solving nonlinear differential equations with differentiable quantum circuits
• NetGAN: Generating Graphs via Random Walks
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Efficient Arbitrary Simultaneously Entangling Gates on a trapped-ion quantum computer
• Application of Quantum Machine Learning using the Quantum Variational Classifier Method to High Energy Physics Analysis at the LHC on IBM Quantum Computer Simulator and Hardware with 10 qubits
• Quantum embeddings for machine learning
• Classification with Quantum Machine Learning: A Survey
• Neutrino interaction classification with a convolutional neural network in the DUNE far detector
• Quantum semi-supervised generative adversarial network for enhanced data classification
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• Recurrent Quantum Neural Networks
• Quantum Machine Learning and its Supremacy in High Energy Physics
• Laplacian Eigenmaps with variational circuits: a quantum embedding of graph data

Cited by in corpus (8)

• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Machine Learning for Anomaly Detection in Particle Physics
• Unravelling physics beyond the standard model with classical and quantum anomaly detection
• Quantum Architecture Search via Deep Reinforcement Learning
• QuClassi: A Hybrid Deep Neural Network Architecture based on Quantum State Fidelity
• Optimizing Quantum Convolutional Neural Network Architectures for Arbitrary Data Dimension
• A unifying primary framework for quantum graph neural networks from quantum graph states
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction