Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman Hierarchy
quant-ph, cs.LG
Submitted: 2026-06-25
Updated: 2026-10-27
Comments: 10 pages, 4 figures (main text); 35 pages, 9 figures, 14 tables including Supplementary Information. Code available at https://github.com/SnehalRaj/mp-qgnns
License: http://creativecommons.org/licenses/by/4.0/
The gist: Graphs provide a natural language for relational data in chemistry, biology and optimisation.
Terminology
Abstract
Graphs provide a natural language for relational data in chemistry, biology and optimisation. Graph neural networks (GNNs) have driven much of the recent progress in learning from such data through message passing, a single primitive that generalises convolution and attention. Quantum counterparts have been proposed, but with limited connection to message passing and few guarantees on performance or scalability. More broadly, the trainability of variational quantum circuits is a recognised bottleneck for their wide applicability, and pre-training has emerged as one way to address it. Yet for a quantum model to be useful, it must offer expressivity guarantees along with demonstrable scalability. Here we show how a quantum graph neural network can be built to perform message passing, to be permutation equivariant, and to sit at a chosen level of the Weisfeiler-Leman hierarchy, the standard measure of how finely a model can tell graphs apart. We show that, as for classical GNNs, the training can be done first on small graph instances, allowing for a pre-training that can mitigate usual training issues, and its output can be read out at a cost that stays low as the graph grows. We validate the framework in large-scale simulations of up to 56 qubits across three datasets, on synthetic graphs that ordinary message passing cannot separate, on molecular property prediction, and on the travelling salesperson problem. Our framework opens a path for near-term quantum algorithms with theoretical guarantees and practical scalability, bringing the principles of graph learning into quantum circuit design.
Sources
- An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem
- Attention, Learn to Solve Routing Problems!
- How Powerful are Graph Neural Networks?
- From Graphs to Qubits: A Critical Review of Quantum Graph Neural Networks
- Quantum Graph Neural Networks
- Towards Quantum Graph Neural Networks: An Ego-Graph Learning Approach
- Quantum Graph Convolutional Neural Networks
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Train on classical, deploy on quantum: scaling generative quantum machine learning to a thousand qubits
- Fermionic Born Machines: Classical training of quantum generative models based on Fermion Sampling
- Quantum Algorithms for Deep Convolutional Neural Networks
- QuIC: Quantum-Inspired Compound Adapters for Parameter Efficient Fine-Tuning
- Graph Attention Networks
- Scalable On-Hardware Training of Quantum Neural Networks and Application to Clinical Data Imputation
- Quantum machine learning with subspace states
- Hartree-Fock on a superconducting qubit quantum computer
- An Empirical Study of Realized GNN Expressiveness
- Graph Neural Networks on Quantum Computers
Related papers
- Computational regimes in matrix-product-state-based quantum trajectory simulations
- Toward chemically accurate quantum simulations on quantum hardware: A quantum-HPC hybrid approach
- Transversal surface-code game with reconfigurable qubits
- Fulqrum: a generalized framework for quantum subspace diagonalization
- Flux-Activated Resonant Control of a Bosonic Quantum Memory
- Machine learning the effects of many quantum measurements