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:2607.17273

Continuous Time Quantum Walk Propagation for Irregular Temporal Graph Forecasting

Jiaqi Sun, Tianhao Li, Zhihao Bian

quant-phSubmitted Jul 19, 2026• Announced Jul 21, 2026• 0 citations
arXivHTMLPDF

Abstract

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.

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

Continuous-Time Quantum Walks based Graph Neural Network

Yuliang Zhan, Zefeng Gao, Jian Li +2 more

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.

arXiv:2608.20738•ACM International Conference on Information and Knowledge Management (CIKM)•Nov 3, 2026•1 citation

Experimental investigation of equivalent Laplacian and adjacency quantum walks on irregular graphs

Dengke Qu, Lei Xiao, Kunkun Wang +2 more

The continuous-time quantum walk denotes the evolution of a particle on a given graph governed by Schr\"odinger's equation. For different applications, the corresponding Hamiltonian is proportional to either the Laplacian or the adjacency matrix of the graph. The two quantum walks are equivalent on regular graphs, since each vertex has the same degree. However, for irregular graphs, the evolutions of the two quantum walks are generally different. In this paper, we report an experimental investigation of the two quantum walks on irregular graphs with single photons and interferometric networks. We demonstrate that it is possible to obtain equivalent probability distributions with the two quantum walks on specific irregular graphs, where the particle is initially localized at a vertex or uniformly distributed at multiple vertices. Our results not only deepen the understanding of the equivalence between the two quantum walks, but also extend the application of the continuous-time quantum walk.

Physical Review A•Jun 27, 2022•8 citations

Continuous-time quantum walks on dynamic graphs

Rebekah Herrman, Travis S. Humble

Continuous-time quantum walks (CTQWs) on static graphs provide efficient methods for search and sampling as well as a model for universal quantum computation. We consider an extension of CTQWs to the case of dynamic graphs, in which an ordered sequence of graphs governs free evolution of the quantum walk. We then consider how perfect state transfer during the quantum walk can be used to design dynamic graphs that implement a universal set of quantum logic gates. We give explicit examples for a complete logical basis, and we validate implementations using numerical simulations for quantum teleportation and addition circuits. Finally, we discuss the potential for realizing CTQWs on dynamic graphs using actively controlled quantum optical waveguides.

arXiv:1902.01346•Physical Review A•Jul 8, 2019•25 citations

Graph embedding using a quasi-quantum analogue of the hitting times of continuous time quantum walks

David Emms, Richard C. Wilson, Edwin R. Hancock

In this paper, we explore analytically and experimentally a quasi-quantum analogue of the hitting time of the continuous-time quantum walk on a graph. For the classical random walk, the hitting time has been shown to be robust to errors in edge weight structure and to lead to spectral clustering algorithms with improved performance. Our analysis shows that the quasi-quantum analogue of the hitting time of the continuoustime quantum walk can be determined via integrals of the Laplacian spectrum, calculated using Gauss-Laguerre quadrature. We analyse the quantum hitting times with reference to their classical counterpart. Specifically, we explore the graph embeddings that preserve hitting time. Experimentally, we show that the quantum hitting times can be used to emphasise cluster-structure.

Quantum Information and Computation•Mar 1, 2009•9 citations

Equivalent Laplacian and adjacency quantum walks on irregular graphs

Thomas G. Wong, Joshua Lockhart

The continuous-time quantum walk is a particle evolving by Schr\"odinger's equation in discrete space. Encoding the space as a graph of vertices and edges, the Hamiltonian is proportional to the discrete Laplacian. In some physical systems, however, the Hamiltonian is proportional to the adjacency matrix instead. It is well known that these quantum walks are equivalent when the graph is regular, i.e., when each vertex has the same number of neighbors. If the graph is irregular, however, the quantum walks evolve differently. In this paper, we show that for some irregular graphs, if the particle is initially localized at a certain vertex, the probability distributions of the two quantum walks are identical, even though the amplitudes differ. We analytically prove this for a graph with five vertices and a graph with six vertices. By simulating the walks on all 1 018 689 568 simple, connected, irregular graphs with 11 vertices or less, we found 64 graphs with this notion of equivalence. We also give eight infinite families of graphs supporting these equivalent walks.

arXiv:2107.05580•Physical Review A•Oct 25, 2021•6 citations
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.
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.
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.
The continuous-time quantum walk denotes the evolution of a particle on a given graph governed by Schr\"odinger's equation. For different applications, the corresponding Hamiltonian is proportional to either the Laplacian or the adjacency matrix of the graph. The two quantum walks are equivalent on regular graphs, since each vertex has the same degree. However, for irregular graphs, the evolutions of the two quantum walks are generally different. In this paper, we report an experimental investigation of the two quantum walks on irregular graphs with single photons and interferometric networks. We demonstrate that it is possible to obtain equivalent probability distributions with the two quantum walks on specific irregular graphs, where the particle is initially localized at a vertex or uniformly distributed at multiple vertices. Our results not only deepen the understanding of the equivalence between the two quantum walks, but also extend the application of the continuous-time quantum walk.
Continuous-time quantum walks (CTQWs) on static graphs provide efficient methods for search and sampling as well as a model for universal quantum computation. We consider an extension of CTQWs to the case of dynamic graphs, in which an ordered sequence of graphs governs free evolution of the quantum walk. We then consider how perfect state transfer during the quantum walk can be used to design dynamic graphs that implement a universal set of quantum logic gates. We give explicit examples for a complete logical basis, and we validate implementations using numerical simulations for quantum teleportation and addition circuits. Finally, we discuss the potential for realizing CTQWs on dynamic graphs using actively controlled quantum optical waveguides.
In this paper, we explore analytically and experimentally a quasi-quantum analogue of the hitting time of the continuous-time quantum walk on a graph. For the classical random walk, the hitting time has been shown to be robust to errors in edge weight structure and to lead to spectral clustering algorithms with improved performance. Our analysis shows that the quasi-quantum analogue of the hitting time of the continuoustime quantum walk can be determined via integrals of the Laplacian spectrum, calculated using Gauss-Laguerre quadrature. We analyse the quantum hitting times with reference to their classical counterpart. Specifically, we explore the graph embeddings that preserve hitting time. Experimentally, we show that the quantum hitting times can be used to emphasise cluster-structure.
The continuous-time quantum walk is a particle evolving by Schr\"odinger's equation in discrete space. Encoding the space as a graph of vertices and edges, the Hamiltonian is proportional to the discrete Laplacian. In some physical systems, however, the Hamiltonian is proportional to the adjacency matrix instead. It is well known that these quantum walks are equivalent when the graph is regular, i.e., when each vertex has the same number of neighbors. If the graph is irregular, however, the quantum walks evolve differently. In this paper, we show that for some irregular graphs, if the particle is initially localized at a certain vertex, the probability distributions of the two quantum walks are identical, even though the amplitudes differ. We analytically prove this for a graph with five vertices and a graph with six vertices. By simulating the walks on all 1 018 689 568 simple, connected, irregular graphs with 11 vertices or less, we found 64 graphs with this notion of equivalence. We also give eight infinite families of graphs supporting these equivalent walks.