基于图的自适应神经网络的量子机器学习

Jincheng Zhang

Published Aug 31, 2026• 0 citations

Abstract

This paper explores the integration of graph neural networks (GNNs) with quantum machine learning (QML) to address the challenges of complex data analysis. We propose a novel framework that utilizes a graph-structured neural network as the primary input for a quantum computation, enabling rapid pattern discovery and automated parameter adjustment. The core mechanism centers on leveraging quantum parallelism to accelerate the learning process within the GNN architecture. The paper details the implementation of the framework, discusses its performance compared to classical methods, and outlines potential applications across diverse data types. We demonstrate that this hybrid approach offers a significant advantage in learning and predicting intricate relationships within complex graph structures. This work represents a step towards a paradigm shift in data analysis, combining the strengths of both graph theory and quantum computation.

DOI: 10.5281/zenodo.22200774

Related papers

基于量子自适应的图神经网络

Jincheng Zhang

This paper introduces a novel approach to graph neural networks (GNNs) – the 'Quantum Adaptive Graph Neural Network' – leveraging quantum self-adaptation to enhance both expressiveness and computational efficiency. Traditional GNNs often struggle with the inherent complexities of graph data and require substantial computational resources. We propose a new architecture that employs quantum mechanics to simulate graph structures, allowing the network to learn more robust representations. This approach, dubbed Quantum Adaptive Graph Neural Network (QAGNN), utilizes quantum machine learning algorithms to improve the network's ability to capture intricate relationships within the graph. The paper details the core mechanism, its mathematical foundations, and preliminary experimental results demonstrating significant improvements in various graph classification tasks compared to traditional GNNs. We present a comprehensive analysis of the QAGNN's performance and discuss potential future research directions.

Aug 31, 20260 citations

基于量子机器学习的图神经网络

Jincheng Zhang

This paper investigates the application of quantum machine learning to graph neural networks (GNNs), specifically focusing on the design and evaluation of a novel quantum-enhanced GNN architecture. We propose a quantum-inspired neural network architecture that leverages the inherent quantum properties of entangled states and superposition to improve the representation capacity and computational efficiency of GNNs. The core mechanism centers around simulating graph structures using quantum algorithms and incorporating quantum machine learning techniques to enhance the network's ability to capture complex relationships within the data. This work introduces a framework for leveraging quantum mechanics to boost the performance of GNNs, potentially offering a significant advancement over traditional approaches. The paper presents initial results demonstrating the efficacy of this quantum-enhanced GNN architecture in a benchmark dataset, highlighting the potential for improved representation and faster training times.

Aug 31, 20260 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

Quantum Graph Neural Network Adaptive Learning

Jincheng Zhang

Quantum Graph Neural Network Adaptive Learning is a novel framework for training graph neural networks (GNNs) through an adaptive learning process. Traditional GNN models rely heavily on classical computer computations, limiting their ability to effectively handle complex datasets. This paper introduces a quantum-enhanced GNN architecture that leverages the unique properties of quantum graphs to enable self-adaptative learning, resulting in improved model performance across diverse datasets. The core mechanism involves the utilization of quantum phenomena to optimize the training process, thereby overcoming the limitations of classical approaches. This research demonstrates the efficacy of this approach through rigorous analysis and empirical validation, showcasing its potential to significantly enhance the capabilities of GNN models.

Sep 6, 20260 citations

Quantum-Enhanced Graph Neural Networks

Jincheng Zhang

Quantum-Enhanced Graph Neural Networks (QEN) presents a novel approach to graph neural network (GNN) learning, leveraging the principles of quantum entanglement to enhance both the training process and the network's expressive capabilities. This research investigates a method for utilizing entanglement to accelerate training and improve the network's ability to represent complex relationships within graph data. We introduce a new architecture incorporating quantum entanglement-enhanced layer activations, exploring its potential to overcome limitations inherent in classical GNN training. The core mechanism focuses on utilizing entanglement to reduce computational complexity and improve the speed of learning. This work demonstrates promising results through theoretical analysis and preliminary experimental validation, suggesting a significant improvement in both training speed and model performance.

Sep 1, 20260 citations

Quantum-Embedded Graph Neural Network Architecture for Molecular Property Prediction

Min Lu, Lei Du, Ziwei Cui +8 more

Accurate prediction of molecular properties is crucial for accelerating the development of new drugs, and quantum machine learning (QML) holds great promise in this domain. A typical QML pipeline comprises two core stages: encoding classical data into quantum representations followed by training and prediction using quantum computing-based machine learning (ML) models. In this article, we focus on the initial encoding stage and propose an effective quantum feature extraction approach for molecular graph data, introducing quantum node embedding and quantum edge embedding methods. We developed a hybrid quantum-classical ML framework and implemented several quantum-embedded graph neural network (QEGNN) models to evaluate the proposed method. Experiments conducted on three benchmark data sets with diverse molecular property prediction tasks demonstrate that QEGNN models consistently achieve higher accuracy, improved stability, and significantly reduced parameter complexity─hallmarks of quantum advantage. Furthermore, we validate the reliability of the quantum embedding approach on the superconducting quantum processor "Wukong," showing that the models retain stable performance even under the constraints of current noisy quantum hardware. This work highlights the potential of QML and paves the way for the development of universal QML models.

Journal of Chemical Information and ModelingJul 26, 20255 citations