Quantum Graph Neural Networks

Abstract

We introduce Quantum Graph Neural Networks (QGNN), a new class of quantum neural network ansatze which are tailored to represent quantum processes which have a graph structure, and are particularly suitable to be executed on distributed quantum systems over a quantum network. Along with this general class of ansatze, we introduce further specialized architectures, namely, Quantum Graph Recurrent Neural Networks (QGRNN) and Quantum Graph Convolutional Neural Networks (QGCNN). We provide four example applications of QGNNs: learning Hamiltonian dynamics of quantum systems, learning how to create multipartite entanglement in a quantum network, unsupervised learning for spectral clustering, and supervised learning for graph isomorphism classification.

8 pages

References in corpus (28)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Semi-Supervised Classification with Graph Convolutional Networks
• The Quantum Internet
• Inductive Representation Learning on Large Graphs
• Quantum sensing
• Neural Message Passing for Quantum Chemistry
• Gaussian Quantum Information
• Spectral Networks and Locally Connected Networks on Graphs
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• A Quantum Approximate Optimization Algorithm
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Deep Convolutional Networks on Graph-Structured Data
• Quantum computation over continuous variables
• From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz
• Efficient Classical Simulation of Continuous Variable Quantum Information Processes
• How Powerful are Graph Neural Networks?
• Entanglement Detection in the Stabilizer Formalism
• Quantum simulation of time-dependent Hamiltonians and the convenient illusion of Hilbert space
• Hamiltonian Learning and Certification Using Quantum Resources
• Verifying Multipartite Entangled GHZ States via Multiple Quantum Coherences
• Quantum Optimization with a Novel Gibbs Objective Function and Ansatz Architecture Search
• Learning to learn with quantum neural networks via classical neural networks
• Heisenberg-Scaling Measurement Protocol for Analytic Functions with Quantum Sensor Networks
• A Universal Training Algorithm for Quantum Deep Learning
• Quantum simulations of one dimensional quantum systems
• A Quantum Approximate Optimization Algorithm for continuous problems

Cited by in corpus (15)

• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Challenges and Opportunities in Quantum Machine Learning
• Machine Learning for Anomaly Detection in Particle Physics
• Building spatial symmetries into parameterized quantum circuits for faster training
• Graph neural network initialisation of quantum approximate optimisation
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Quantum utility -- definition and assessment of a practical quantum advantage
• On the universality of $S_n$-equivariant $k$-body gates
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• Trade-off between Gradient Measurement Efficiency and Expressivity in Deep Quantum Neural Networks
• QFCNN: Quantum Fourier Convolutional Neural Network
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• Learning to Utilize Correlated Auxiliary Noise: A Possible Quantum Advantage
• Towards graph classification with Gaussian Boson Sampling by embedding graphs on the X8 photonic chip