arXiv:2411.16354 · Physical Review Letters

Scalable Parameter Design for Superconducting Quantum Circuits with Graph Neural Networks

Hao Ai, Yu-xi Liu

Published Jun 25, 2025• 8 citations

Abstract

To demonstrate supremacy of quantum computing, increasingly large-scale superconducting quantum computing chips are being designed and fabricated. However, the complexity of simulating quantum systems poses a significant challenge to computer-aided design of quantum chips, especially for large-scale chips. Harnessing the scalability of graph neural networks (GNNs), we here propose a parameter designing algorithm for large-scale superconducting quantum circuits. The algorithm depends on the so-called "three-stair scaling" mechanism, which comprises two neural-network models: an evaluator supervisedly trained on small-scale circuits for applying to medium-scale circuits, and a designer unsupervisedly trained on medium-scale circuits for applying to large-scale ones. We demonstrate our algorithm in mitigating quantum crosstalk errors. Frequencies for both single- and two-qubit gates (corresponding to the parameters of nodes and edges) are considered simultaneously. Numerical results indicate that the well-trained designer achieves notable advantages in efficiency, effectiveness, and scalability. For example, for large-scale superconducting quantum circuits consisting of around 870 qubits, our GNNs-based algorithm achieves 51% of the errors produced by the state-of-the-art algorithm, with a time reduction from 90 min to 27 s. Overall, a better-performing and more scalable algorithm for designing parameters of superconducting quantum chips is proposed, which demonstrates the advantages of applying GNNs in superconducting quantum chips.

DOI: 10.1103/yr9d-7z8k

Related papers

Graph Neural Networks for Parameterized Quantum Circuits Expressibility Estimation

Shamminuj Aktar, Andreas Bärtschi, Diane Oyen +2 more

Parameterized quantum circuits (PQCs) are fundamental to quantum machine learning (QML), quantum optimization, and variational quantum algorithms (VQAs). The expressibility of PQCs is a measure that determines their capability to harness the full potential of the quantum state space. It is thus a crucial guidepost to know when selecting a particular PQC ansatz. However, the existing technique for expressibility computation through statistical estimation requires a large number of samples, which poses significant challenges due to time and computational resource constraints. This paper introduces a novel approach for expressibility estimation of PQCs using Graph Neural Networks (GNNs). We demonstrate the predictive power of our GNN model with a dataset consisting of 25,000 samples from the noiseless IBM QASM Simulator and 12,000 samples from three distinct noisy quantum backends. The model accurately estimates expressibility, with root mean square errors (RMSE) of 0.05 and 0.06 for the noiseless and noisy backends, respectively. We compare our model's predictions with reference circuits from Sim et al. and IBM Qiskit's hardware-efficient ansatz sets to further evaluate our model's performance. Our experimental evaluation in noiseless and noisy scenarios reveals a close alignment with ground truth expressibility values, highlighting the model's efficacy. Moreover, our model exhibits promising extrapolation capabilities, predicting expressibility values with low RMSE for out-of-range qubit circuits trained solely on only up to 5-qubit circuit sets. This work thus provides a reliable means of efficiently evaluating the expressibility of diverse PQCs on noiseless simulators and hardware.

arXiv:2405.08100IEEE International Conference on Quantum Computing and Engineering (QCE)Sep 15, 20242 citations

Graph Neural Networks on Quantum Computers

Yidong Liao, Xiao‐Ming Zhang, Christopher Ferrie

Graph Neural Networks (GNNs) are powerful machine learning models that excel at analyzing structured data represented as graphs, demonstrating remarkable performance in applications like social network analysis and recommendation systems. However, classical GNNs face scalability challenges when dealing with large-scale graphs. This paper proposes frameworks for implementing GNNs on quantum computers to potentially address the challenges. We devise quantum algorithms corresponding to the three fundamental types of classical GNNs: Graph Convolutional Networks, Graph Attention Networks, and Message-Passing GNNs. A complexity analysis of our quantum implementation of the Simplified Graph Convolutional (SGC) Network shows potential quantum advantages over its classical counterpart, with significant improvements in time and space complexities. Our complexities can have trade-offs between the two: when optimizing for minimal circuit depth, our quantum SGC achieves logarithmic time complexity in the input sizes (albeit at the cost of linear space complexity). When optimizing for minimal qubit usage, the quantum SGC exhibits space complexity logarithmic in the input sizes, offering an exponential reduction compared to classical SGCs, while still maintaining better time complexity. These results suggest our Quantum GNN frameworks could efficiently process large-scale graphs. This work paves the way for implementing more advanced Graph Neural Network models on quantum computers, opening new possibilities in quantum machine learning for analyzing graph-structured data.

arXiv:2405.17060May 27, 20242 citations

Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman Hierarchy

Snehal Raj, Brian Coyle, Léo Monbroussou +3 more

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.

quant-pharXiv:2606.26873Jun 26, 20260 citations

S-Parameter-Based Simulation Technique and Crosstalk Suppression for Large-Scale Superconducting Quantum-Computing Chip Design

Shoichi Shiba, Shuhei Tamate, Peter Spring +5 more

The increasing size of superconducting quantumcomputer chips requires a shift in evaluation methods for chip design. Three-dimensional (3D) electromagnetic (EM) simulations become computationally intractable as model size increases owing to the exponential growth in computation time. To address this challenge, we develop a technique that analyzes the circuit parameters of large-scale superconducting qubit chips by combining S-parameters simulated in smaller-scale 3D EM models. Herein, we design a four-qubit unit cell for large-scale qubit devices and evaluate both residual qubit-qubit coupling and control-line-to-qubit crosstalk for distant qubit pairs. In addition, we propose guard structures around qubits to mitigate nearestneighbor crosstalk. Although previous methods are limited to chips with at most ten qubits, our approach enables the analysis of systems with over a hundred qubits.

IEEE MTT-S International Microwave Symposium digestJun 15, 20250 citations

Quantum Circuit Verification via Graph Neural Networks

Jincheng Zhang

The verification of quantum circuits is a critical step in ensuring the reliable execution of quantum computations. Traditional methods often struggle with the exponential complexity arising from the superposition and entanglement inherent in quantum mechanics. This work proposes a novel approach utilizing Graph Neural Networks (GNNs) to address this challenge. Quantum circuits are represented as graphs, where nodes correspond to quantum gates and edges represent data flow. The GNN learns to identify patterns within these graph representations that signify potential errors or deviations from the intended circuit behavior. This automated verification process offers a scalable solution compared to exhaustive simulation or analytical methods. The core of this approach lies in leveraging the expressive power of GNNs to capture complex correlations within the circuit structure, ultimately leading to more efficient and accurate verification. We demonstrate the feasibility and effectiveness of this methodology through a theoretical framework and outline future research directions.

Sep 1, 20260 citations

Graph Neural Networks for Quantum State Simulation

Jincheng Zhang

Quantum state simulation is a cornerstone of quantum computing, aiming to accurately represent and manipulate the behavior of quantum systems. However, traditional methods of quantum state simulation, such as the Density Matrix Renormalization Group (DMRG) method and the Variational Quantum Eigensolver (VQE), often suffer from significant computational challenges, particularly as the size of the quantum system increases. This paper proposes a novel approach to quantum state simulation leveraging the power of Graph Neural Networks (GNNs). We represent a quantum state as a graph, where nodes correspond to individual quantum states and edges represent the correlations between them. A GNN is then trained to learn the complex relationships within the quantum state, enabling efficient and scalable simulation. Our method significantly reduces the computational burden associated with traditional techniques, offering a promising path towards practical quantum state simulation. The core claim is the utilization of graph neural networks' structural information for efficient quantum state simulation. The core mechanism involves representing quantum states as nodes in a graph and employing GNNs to learn relationships between them, facilitating efficient quantum state simulation.

Sep 3, 20260 citations