Quantum Graph Neural Networks

TL;DR

This paper introduces Quantum Graph Neural Networks (QGNN), a novel class of quantum neural networks designed for graph-structured quantum processes, suitable for distributed quantum systems and including specialized architectures like QGRNN and QGCNN.

Contribution

The paper proposes the QGNN framework and its variants, demonstrating their applicability to quantum dynamics, entanglement generation, spectral clustering, and graph isomorphism tasks.

Findings

QGNN effectively models quantum processes with graph structures

QGNN architectures can learn Hamiltonian dynamics and entanglement

Applications include spectral clustering and graph classification

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.