Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2608.20738 · ACM International Conference on Information and Knowledge Management (CIKM)

Continuous-Time Quantum Walks based Graph Neural Network

Yuliang Zhan, Zefeng Gao, Jian Li, Yang Liu, Hao sun

Published Nov 3, 2026• 1 citation
arXivHTMLPDF

Abstract

Graph Neural Networks (GNNs) are widely used on graph-structured data. However, most GNNs suffer from two key weaknesses. First, message passing acts as a low-pass filter based on the homophily assumption, so it performs poorly on heterophilic graphs, where connected nodes differ. Second, stacking layers makes node features converge exponentially to constants, a problem known as oversmoothing. Existing work usually addresses the two weaknesses separately. The few methods that target both rely on empirical heuristics, and many over-smoothing solutions further sacrifice the expressive power of the model. To address both weaknesses with theoretical justification, we propose CTQW-GNN, a GNN built on Continuous-Time Quantum Walks (CTQW). The design is motivated by two properties of the CTQW propagator e-iHt. (i) It is unitary and its eigenvalues lie on the unit circle, so no frequency component is damped. This directly counters the low-pass bias. (ii) Unitarity preserves the feature norm, so the Dirichlet energy does not decay exponentially with depth. This directly counters oversmoothing. Guided by these properties, CTQW-GNN combines three aggregation modules, each motivated by a specific gap in prior work. CTQW-based Aggregation evolves node features through the unitary propagator. It captures the mid- and high-frequency signals needed for heterophilic graphs and provably keeps the Dirichlet energy from collapsing, so it addresses both weaknesses in a single branch. CTQW-Attention Aggregation builds a multi-hop neighbor graph from the CTQW amplitudes and applies attention over it, so distant homophilic nodes that single-hop aggregation misses can still be reached. LF Aggregation is a standard low-pass branch (GAT) that preserves accuracy on strongly homophilic graphs, where a pure CTQW branch is suboptimal. We further provide a spectralgap analysis that explains the energy preservation, and a Lieb– Robinson-type bound that gives a principled rule for choosing the walk-time t . Experiments on 14 benchmarks (9 heterophilic, 5 homophilic) show that CTQW-GNN reaches state-of-the-art accuracy on every dataset. Krylov propagation and Chebyshev-based sparsification keep the CTQW-related computation linear in the number of edges under the stated sparsification rule.

DOI
10.1145/3799682.3840936

Related papers

CTQWformer: A CTQW-based Transformer for Graph Classification

Zhan Li, Wuqing Yu, Yusen Wu +1 more

Graph Neural Networks (GNN) and Transformer-based architectures have achieved remarkable progress in graph learning, yet they still struggle to capture both global structural dependencies and model the dynamic information propagation. In this paper, we propose CTQWformer, a hybrid graph learning framework that integrates continuous-time quantum walks (CTQW) with GNN. CTQWformer employs a trainable Hamiltonian that fuses graph topology and node features, enabling physically grounded modeling of quantum walk dynamics that captures rich and intricate graph structure information. The extracted CTQW-based representations are incorporated into two complementary modules:(i) a Graph Transformer module that embeds final-time propagation probabilities as structural biases in the self-attention mechanism, and (ii) a Graph Recurrent Module that captures temporal evolution patterns with bidirectional recurrent networks. Extensive experiments on benchmark graph classification datasets demonstrate that CTQWformer outperforms graph kernel and GNN-based methods, demonstrating the potential of integrating quantum dynamics into trainable deep learning frameworks for graph representation learning. To the best of our knowledge, CTQWformer is the first hybrid CTQW-based Transformer, integrating CTQW-derived structural bias with temporal evolution modeling to advance graph learning.

cs.LGCross-listedarXiv:2605.09486•May 12, 2026•0 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:2606.26873•Jun 26, 2026•0 citations

Continuous Time Quantum Walk Propagation for Irregular Temporal Graph Forecasting

Jiaqi Sun, Tianhao Li, Zhihao Bian

Continuous time quantum walks built on graph Laplacians produce non monotonic graph propagation features through quantum interference during evolution, which classical diffusion cannot achieve. Such walks deliver a physically motivated propagation scheme for temporal graph signal modeling. We propose Quantum Walk Temporal Architecture (QWTA), which replaces classical graph propagation with a CTQW-type parameterized spectral propagator. QWTA embeds effective observation intervals into the spectral phase modulation of the propagation kernel. QWTA-Base preserves exact CTQW spectral evolution and serves as a physically faithful propagation reference. QWTA-GR further introduces phase soft clipping and gated residual fusion to stabilize propagation. The results show that explicit phase encoding of irregular time intervals, when combined with suitable stabilization, provides a physically motivated and competitive graph propagation design for temporal graph forecasting with missing historical observations.

quant-pharXiv:2607.17273•Jul 21, 2026•0 citations

A Continuous - Time Quantum Walk for Attributed Graphs Matching

Tewabe Chekole Workneh

Diverse facets Of the Theory of Quantum Walks on Graph are reviewed Till now .In specific, Quantum network routing, Quantum Walk Search Algorithm, Element distinctness associated to the eigenvalues of Graphs and the use of these relation /connection in the study of Quantum walks is furthermore described. Different Researchers had contribution and put their benchmark idea Pertaining with this research concept. I furthermore try to investigate recent Application of Quantum walks, In specific the problem pertained with Graph matching i.e Matching nodes(vertices) of the Graphs. In this research paper,I consider how Continuous-time quantum walk (CTQW) can be directed to Graph-matching problems. The matching problem is abstracted using weighted(attributed) Graphs that connects vertices's of one Graph to other and Try to compute the distance b/n those Graphs Node's Beside that finding the matched nodes and the Cost related to Matching. eventually measuring the distance between two Graphs which might have different size then by using k-nearest neighbor (k-NN) method try to classifying those graph based on closest training examples in the feature space.

arXiv:1801.10339•Jan 31, 2018•1 citation

Quantum-enhanced learning: Leveraging von Neumann entropy for enhanced graph neural network performance

Muhammad Awais, Octavian Adrian Postolache, Sancho Moura Oliveira

Graph Neural Networks (GNNs) have established themselves as powerful tools for learning from graph-structured data. However, their reliance on local message-passing mechanisms leads to over-squashing-the compression of exponentially growing neighborhood information into fixed-size vectors-which severely limits long-range dependency modeling. We introduce the Quantum-Inspired Graph Neural Network (QGNN) with a novel Quantum Entanglement Loss (QEL) function that addresses this challenge through a fundamentally different mechanism than existing approaches. Unlike spectral regularization (which enforces smoothness) or maximum entropy methods (which encourage representation diversity), QEL minimizes the von Neumann entropy of the node embedding correlation matrix, thereby concentrating eigenvalues in dominant eigenmodes that preserve global structural patterns. This entropy minimization creates direct information pathways between distant but functionally related nodes, effectively bypassing multi-hop bottlenecks. We evaluate QGNN on both standard benchmarks (Cora, Citeseer, PPI, Electronic Circuits) and the Long Range Graph Benchmark (LRGB) suite, which features graphs with average diameters up to 56.99 (Peptides). On LRGB datasets, QGNN achieves substantial improvements: 37.6% relative MAE reduction on Peptides-struct compared to GCN, 4.0% improvement over Graph Transformers (GraphGPS), and notably, 97% better performance than GCN on node pairs separated by 7+ hops. Despite these gains, QGNN requires only 20-30% additional computational overhead compared to standard GCN, while being 5-6 × faster than Graph Transformer approaches. Our results establish entropy-based regularization as a principled and efficient approach for long-range dependency modeling in graphs.

Neural Networks•Apr 9, 2026•0 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:2405.17060•May 27, 2024•16 citations
Graph Neural Networks (GNNs) are widely used on graph-structured data. However, most GNNs suffer from two key weaknesses. First, message passing acts as a low-pass filter based on the homophily assumption, so it performs poorly on heterophilic graphs, where connected nodes differ. Second, stacking layers makes node features converge exponentially to constants, a problem known as oversmoothing. Existing work usually addresses the two weaknesses separately. The few methods that target both rely on empirical heuristics, and many over-smoothing solutions further sacrifice the expressive power of the model. To address both weaknesses with theoretical justification, we propose CTQW-GNN, a GNN built on Continuous-Time Quantum Walks (CTQW). The design is motivated by two properties of the CTQW propagator e-iHt. (i) It is unitary and its eigenvalues lie on the unit circle, so no frequency component is damped. This directly counters the low-pass bias. (ii) Unitarity preserves the feature norm, so the Dirichlet energy does not decay exponentially with depth. This directly counters oversmoothing. Guided by these properties, CTQW-GNN combines three aggregation modules, each motivated by a specific gap in prior work. CTQW-based Aggregation evolves node features through the unitary propagator. It captures the mid- and high-frequency signals needed for heterophilic graphs and provably keeps the Dirichlet energy from collapsing, so it addresses both weaknesses in a single branch. CTQW-Attention Aggregation builds a multi-hop neighbor graph from the CTQW amplitudes and applies attention over it, so distant homophilic nodes that single-hop aggregation misses can still be reached. LF Aggregation is a standard low-pass branch (GAT) that preserves accuracy on strongly homophilic graphs, where a pure CTQW branch is suboptimal. We further provide a spectralgap analysis that explains the energy preservation, and a Lieb– Robinson-type bound that gives a principled rule for choosing the walk-time t . Experiments on 14 benchmarks (9 heterophilic, 5 homophilic) show that CTQW-GNN reaches state-of-the-art accuracy on every dataset. Krylov propagation and Chebyshev-based sparsification keep the CTQW-related computation linear in the number of edges under the stated sparsification rule.
Graph Neural Networks (GNN) and Transformer-based architectures have achieved remarkable progress in graph learning, yet they still struggle to capture both global structural dependencies and model the dynamic information propagation. In this paper, we propose CTQWformer, a hybrid graph learning framework that integrates continuous-time quantum walks (CTQW) with GNN. CTQWformer employs a trainable Hamiltonian that fuses graph topology and node features, enabling physically grounded modeling of quantum walk dynamics that captures rich and intricate graph structure information. The extracted CTQW-based representations are incorporated into two complementary modules:(i) a Graph Transformer module that embeds final-time propagation probabilities as structural biases in the self-attention mechanism, and (ii) a Graph Recurrent Module that captures temporal evolution patterns with bidirectional recurrent networks. Extensive experiments on benchmark graph classification datasets demonstrate that CTQWformer outperforms graph kernel and GNN-based methods, demonstrating the potential of integrating quantum dynamics into trainable deep learning frameworks for graph representation learning. To the best of our knowledge, CTQWformer is the first hybrid CTQW-based Transformer, integrating CTQW-derived structural bias with temporal evolution modeling to advance graph learning.
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.
Continuous time quantum walks built on graph Laplacians produce non monotonic graph propagation features through quantum interference during evolution, which classical diffusion cannot achieve. Such walks deliver a physically motivated propagation scheme for temporal graph signal modeling. We propose Quantum Walk Temporal Architecture (QWTA), which replaces classical graph propagation with a CTQW-type parameterized spectral propagator. QWTA embeds effective observation intervals into the spectral phase modulation of the propagation kernel. QWTA-Base preserves exact CTQW spectral evolution and serves as a physically faithful propagation reference. QWTA-GR further introduces phase soft clipping and gated residual fusion to stabilize propagation. The results show that explicit phase encoding of irregular time intervals, when combined with suitable stabilization, provides a physically motivated and competitive graph propagation design for temporal graph forecasting with missing historical observations.
Diverse facets Of the Theory of Quantum Walks on Graph are reviewed Till now .In specific, Quantum network routing, Quantum Walk Search Algorithm, Element distinctness associated to the eigenvalues of Graphs and the use of these relation /connection in the study of Quantum walks is furthermore described. Different Researchers had contribution and put their benchmark idea Pertaining with this research concept. I furthermore try to investigate recent Application of Quantum walks, In specific the problem pertained with Graph matching i.e Matching nodes(vertices) of the Graphs. In this research paper,I consider how Continuous-time quantum walk (CTQW) can be directed to Graph-matching problems. The matching problem is abstracted using weighted(attributed) Graphs that connects vertices's of one Graph to other and Try to compute the distance b/n those Graphs Node's Beside that finding the matched nodes and the Cost related to Matching. eventually measuring the distance between two Graphs which might have different size then by using k-nearest neighbor (k-NN) method try to classifying those graph based on closest training examples in the feature space.
Graph Neural Networks (GNNs) have established themselves as powerful tools for learning from graph-structured data. However, their reliance on local message-passing mechanisms leads to over-squashing-the compression of exponentially growing neighborhood information into fixed-size vectors-which severely limits long-range dependency modeling. We introduce the Quantum-Inspired Graph Neural Network (QGNN) with a novel Quantum Entanglement Loss (QEL) function that addresses this challenge through a fundamentally different mechanism than existing approaches. Unlike spectral regularization (which enforces smoothness) or maximum entropy methods (which encourage representation diversity), QEL minimizes the von Neumann entropy of the node embedding correlation matrix, thereby concentrating eigenvalues in dominant eigenmodes that preserve global structural patterns. This entropy minimization creates direct information pathways between distant but functionally related nodes, effectively bypassing multi-hop bottlenecks. We evaluate QGNN on both standard benchmarks (Cora, Citeseer, PPI, Electronic Circuits) and the Long Range Graph Benchmark (LRGB) suite, which features graphs with average diameters up to 56.99 (Peptides). On LRGB datasets, QGNN achieves substantial improvements: 37.6% relative MAE reduction on Peptides-struct compared to GCN, 4.0% improvement over Graph Transformers (GraphGPS), and notably, 97% better performance than GCN on node pairs separated by 7+ hops. Despite these gains, QGNN requires only 20-30% additional computational overhead compared to standard GCN, while being 5-6 × faster than Graph Transformer approaches. Our results establish entropy-based regularization as a principled and efficient approach for long-range dependency modeling in graphs.
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.