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

Chinese journal of information fusion.

Knowledge Graph Reasoning with Quantum-Inspired Reinforcement Learning

Junliang Chen, Xianchao Zhang, Fengsong Sun, Jun Yong Lu

Published May 25, 2025• 1 citation
Publisher

Abstract

Knowledge reasoning is a critical task in information fusion systems, and its core step is reasoning missing information from existing facts to improve the knowledge graphs. Embedding-based reasoning methods and path-based reasoning methods are two mainstream knowledge reasoning methods. Embedding-based reasoning methods enable fast and direct reasoning but are limited to simple relationships between entities and exhibit poor performance in reasoning complex logical relationships. Path-based reasoning methods perform better in complex reasoning tasks, but suffer from high computational complexity, a large number of model parameters, and low reasoning efficiency. To address the aforementioned issues, this paper introduces a knowledge reasoning model called Quantum-Inspired Reinforcement Learning (QIRL). QIRL leverages quantum reinforcement learning to train a strategy network via a quantum circuit, aiming to generate and optimize reasoning paths. Quantum circuit achieves complex nonlinear operations through limited quantum reasoning paths gate operations, reducing computational complexity. In addition, this article utilizes the quantum entanglement property to encode high-dimensional data, reducing the number of model training parameters. This article evaluates the QIRL method on entity prediction task and proves that the QIRL method can effectively reduce the number of model training parameters.

DOI
10.62762/cjif.2025.552445

Related papers

Quantum-Inspired Reinforcement Learning for Edge-Driven Cyber-Physical Systems

Jagjit Singh Dhatterwal, Sandeep Kumar, Shilpa Choudhary

The integration of Quantum-Inspired Reinforcement Learning (QiRL) into Edge-Driven CyberPhysical Systems (CPS) presents a transformative approach to enhance real-time decision-making in distributed environments. While classical reinforcement learning (RL) struggles with scalability and computational complexity in edge-CPS, quantum-inspired Quantum-Inspired Reinforcement Learning for Edge-Driven Cyber-Physical Systems algorithms leverage superposition and entanglement principles to optimize policy exploration and convergence. This paper proposes a novel QiRL framework that combines quantum-inspired optimization with deep RL, enabling efficient resource allocation and adaptive control in latency-sensitive applications (e.g., smart grids, autonomous drones). We formalize the mathematical foundations of QiRL, design a hybrid neural-quantum architecture for edge deployment, and evaluate its performance under dynamic CPS constraints. Simulations on IoT-based case studies demonstrate $\mathbf{2 0}-\mathbf{3 5 \%}$ faster convergence and $\mathbf{1 5 \%}$ higher energy efficiency compared to classical Deep Q-Networks (DQN). Key challenges, such as quantum noise simulation and edge-hardware limitations, are discussed to guide future research. This work bridges quantum computing principles with edge intelligence, offering a scalable pathway for nextgeneration CPS.

International Conference on Mobile Networks and Wireless Communications (ICMNWC)•Dec 10, 2025•0 citations

Fast Variational Knowledge Graph Embedding

Pulak Ranjan Giri, Mori Kurokawa, Kazuhiro Saito

Embedding of a knowledge graph(KG) entities and relations in the form of vectors is an important aspect for the manipulation of the KG database for several downstream tasks, such as link prediction, knowledge graph completion, and recommendation. Because of the growing size of the knowledge graph databases, it has become a daunting task for the classical computer to train a model efficiently. Quantum computer can help speedup the embedding process of the KGs by encoding the entities into a variational quantum circuit of polynomial depth. Usually, the time complexity for such variational circuit-dependent quantum classical algorithms for each epoch is O(Npoly(logM)), where$N$is number of elements in the knowledge graph and$M$is the number of features of each entities of the knowledge graph. In this article we exploit additional quantum advantage by training multiple elements of KG in superpositions, thereby reducing the computing time further for the knowledge graph embedding model.

arXiv:2507.02472•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 15, 2024•0 citations

QTRL: Toward Practical Quantum Reinforcement Learning via Quantum-Train

Chen-Yu Liu, Chu-Hsuan Abraham Lin, Chao-Han Huck Yang +2 more

Quantum reinforcement learning utilizes quantum layers to process information within a machine learning model. However, both pure and hybrid quantum reinforcement learning face challenges such as data encoding and the use of quantum computers during the inference stage. We apply the Quantum-Train method to reinforcement learning tasks, called QTRL, training the classical policy network model using a quantum machine learning model with polylogarithmic parameter reduction. This QTRL approach eliminates the data encoding issues of conventional quantum machine learning and reduces the training parameters of the corresponding classical policy network. Most importantly, the training result of the QTRL is a classical model, meaning the inference stage only requires classical computer. This is extremely practical and cost-efficient for reinforcement learning tasks, where low-latency feedback from the policy model is essential.

arXiv:2407.06103•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 15, 2024•40 citations

Quantum-Inspired Reinforcement Learning for Quantum Control

Haixu Yu, Xudong Zhao, Chunlin Chen

Reinforcement learning (RL) is considered a powerful technology with the potential to revolutionize quantum control. However, the application effectiveness of traditional RL is often limited by some insurmountable experimental conditions. Thus, developing new RL algorithms that can efficiently manipulate the quantum system dynamics is a crucial task. Prior research has shown that incorporating quantum mechanical properties into RL can improve learning performance. In this article, we consider the quantum control problem where only the target state can be accurately identified and introduce a quantum-inspired RL (QiRL) method. In particular, we propose a quantum-inspired exploration strategy to replace a commonly used$\epsilon $-greedy strategy, as well as a quantum-inspired reward scheme to incentivize the learning agent. Numerical results on three quantum system control problems, i.e., one-qubit closed quantum system, two-level open quantum system, and many-qubit closed quantum system, verify the effectiveness of QiRL. Comparison results show that the proposed QiRL outperforms existing RL algorithms (deep Q-network and proximal policy optimization) in terms of stability and efficiency for solving quantum control problems.

IEEE Transactions on Control Systems Technology•Aug 14, 2024•15 citations

Quantum-Inspired Relational Reasoning for Knowledge Graphs

Jincheng Zhang

Knowledge graphs (KGs) are increasingly utilized for representing and reasoning over complex data. Traditional relational reasoning methods within KGs often struggle with scalability and efficiency, particularly when dealing with large and intricate graph structures. This paper proposes a novel approach to relational reasoning in KGs by incorporating quantum-inspired techniques. Specifically, we explore the application of Grover's search algorithm to accelerate the traversal and inference processes. Our core claim is that leveraging quantum-inspired algorithms can significantly improve the performance of querying and reasoning within KGs. We present a framework for adapting Grover's algorithm to KG traversal and inference, outlining the key steps and considerations. The resulting system demonstrates the potential for enhanced efficiency compared to traditional symbolic reasoning, particularly in scenarios with high computational complexity. We provide a detailed mathematical formulation of the underlying concepts and algorithms. The primary contribution of this work lies in demonstrating a viable pathway to harnessing the power of quantum-inspired methods for relational reasoning in knowledge graphs, opening possibilities for more scalable and intelligent knowledge representation and reasoning systems.

•Aug 28, 2026•0 citations

Harnessing Quantum Computing to Optimize Reinforcement Learning for NLP Tasks

Kranthi Kumar Lella, Mallu Shiva Rama Krishna

Reinforcement Learning has proven to be promising for training agents in Natural Language Processing to learn and evolve in complex language spaces. However, traditional Reinforcement Learning methods have limitations such as slow learning and high computational costs. In particular large scale NLP problems, Reinforcement Learning may encounter various issues. The reserach presents a method that addresses these limitations, which we refer to as Harnessing Quantum Computing to Optimize Reinforcement Learning for NLP Tasks. We combine quantum computing and classical computing to take advantage of quantum properties such as superposition, quantum entanglement, and Grover’s search algorithm to improve learning. Reinforcement Learning combines quantum-enhanced quantum function and quantum-based circuit to accelerate achievement and evaluate applications. We demonstrate experiments’ applicability, achievement, and scalability with state-of-the-art NLP problems: sentiment analysis, named entity recognition, and language modeling. The quantum enhanced learning model could deliver for practical applications fast learning and good accuracy in solving those problems than standard and quantum models.

International Conference on Artificial Intelligence and Signal Processing (AISP)•Nov 22, 2025•1 citation
Knowledge reasoning is a critical task in information fusion systems, and its core step is reasoning missing information from existing facts to improve the knowledge graphs. Embedding-based reasoning methods and path-based reasoning methods are two mainstream knowledge reasoning methods. Embedding-based reasoning methods enable fast and direct reasoning but are limited to simple relationships between entities and exhibit poor performance in reasoning complex logical relationships. Path-based reasoning methods perform better in complex reasoning tasks, but suffer from high computational complexity, a large number of model parameters, and low reasoning efficiency. To address the aforementioned issues, this paper introduces a knowledge reasoning model called Quantum-Inspired Reinforcement Learning (QIRL). QIRL leverages quantum reinforcement learning to train a strategy network via a quantum circuit, aiming to generate and optimize reasoning paths. Quantum circuit achieves complex nonlinear operations through limited quantum reasoning paths gate operations, reducing computational complexity. In addition, this article utilizes the quantum entanglement property to encode high-dimensional data, reducing the number of model training parameters. This article evaluates the QIRL method on entity prediction task and proves that the QIRL method can effectively reduce the number of model training parameters.
The integration of Quantum-Inspired Reinforcement Learning (QiRL) into Edge-Driven CyberPhysical Systems (CPS) presents a transformative approach to enhance real-time decision-making in distributed environments. While classical reinforcement learning (RL) struggles with scalability and computational complexity in edge-CPS, quantum-inspired Quantum-Inspired Reinforcement Learning for Edge-Driven Cyber-Physical Systems algorithms leverage superposition and entanglement principles to optimize policy exploration and convergence. This paper proposes a novel QiRL framework that combines quantum-inspired optimization with deep RL, enabling efficient resource allocation and adaptive control in latency-sensitive applications (e.g., smart grids, autonomous drones). We formalize the mathematical foundations of QiRL, design a hybrid neural-quantum architecture for edge deployment, and evaluate its performance under dynamic CPS constraints. Simulations on IoT-based case studies demonstrate 20−35%\mathbf{2 0}-\mathbf{3 5 \%}20−35% faster convergence and 15%\mathbf{1 5 \%}15% higher energy efficiency compared to classical Deep Q-Networks (DQN). Key challenges, such as quantum noise simulation and edge-hardware limitations, are discussed to guide future research. This work bridges quantum computing principles with edge intelligence, offering a scalable pathway for nextgeneration CPS.
Embedding of a knowledge graph(KG) entities and relations in the form of vectors is an important aspect for the manipulation of the KG database for several downstream tasks, such as link prediction, knowledge graph completion, and recommendation. Because of the growing size of the knowledge graph databases, it has become a daunting task for the classical computer to train a model efficiently. Quantum computer can help speedup the embedding process of the KGs by encoding the entities into a variational quantum circuit of polynomial depth. Usually, the time complexity for such variational circuit-dependent quantum classical algorithms for each epoch is O(Npoly(logM)), whereNNNis number of elements in the knowledge graph andMMMis the number of features of each entities of the knowledge graph. In this article we exploit additional quantum advantage by training multiple elements of KG in superpositions, thereby reducing the computing time further for the knowledge graph embedding model.
Quantum reinforcement learning utilizes quantum layers to process information within a machine learning model. However, both pure and hybrid quantum reinforcement learning face challenges such as data encoding and the use of quantum computers during the inference stage. We apply the Quantum-Train method to reinforcement learning tasks, called QTRL, training the classical policy network model using a quantum machine learning model with polylogarithmic parameter reduction. This QTRL approach eliminates the data encoding issues of conventional quantum machine learning and reduces the training parameters of the corresponding classical policy network. Most importantly, the training result of the QTRL is a classical model, meaning the inference stage only requires classical computer. This is extremely practical and cost-efficient for reinforcement learning tasks, where low-latency feedback from the policy model is essential.
Reinforcement learning (RL) is considered a powerful technology with the potential to revolutionize quantum control. However, the application effectiveness of traditional RL is often limited by some insurmountable experimental conditions. Thus, developing new RL algorithms that can efficiently manipulate the quantum system dynamics is a crucial task. Prior research has shown that incorporating quantum mechanical properties into RL can improve learning performance. In this article, we consider the quantum control problem where only the target state can be accurately identified and introduce a quantum-inspired RL (QiRL) method. In particular, we propose a quantum-inspired exploration strategy to replace a commonly used$\epsilon $-greedy strategy, as well as a quantum-inspired reward scheme to incentivize the learning agent. Numerical results on three quantum system control problems, i.e., one-qubit closed quantum system, two-level open quantum system, and many-qubit closed quantum system, verify the effectiveness of QiRL. Comparison results show that the proposed QiRL outperforms existing RL algorithms (deep Q-network and proximal policy optimization) in terms of stability and efficiency for solving quantum control problems.
Knowledge graphs (KGs) are increasingly utilized for representing and reasoning over complex data. Traditional relational reasoning methods within KGs often struggle with scalability and efficiency, particularly when dealing with large and intricate graph structures. This paper proposes a novel approach to relational reasoning in KGs by incorporating quantum-inspired techniques. Specifically, we explore the application of Grover's search algorithm to accelerate the traversal and inference processes. Our core claim is that leveraging quantum-inspired algorithms can significantly improve the performance of querying and reasoning within KGs. We present a framework for adapting Grover's algorithm to KG traversal and inference, outlining the key steps and considerations. The resulting system demonstrates the potential for enhanced efficiency compared to traditional symbolic reasoning, particularly in scenarios with high computational complexity. We provide a detailed mathematical formulation of the underlying concepts and algorithms. The primary contribution of this work lies in demonstrating a viable pathway to harnessing the power of quantum-inspired methods for relational reasoning in knowledge graphs, opening possibilities for more scalable and intelligent knowledge representation and reasoning systems.
Reinforcement Learning has proven to be promising for training agents in Natural Language Processing to learn and evolve in complex language spaces. However, traditional Reinforcement Learning methods have limitations such as slow learning and high computational costs. In particular large scale NLP problems, Reinforcement Learning may encounter various issues. The reserach presents a method that addresses these limitations, which we refer to as Harnessing Quantum Computing to Optimize Reinforcement Learning for NLP Tasks. We combine quantum computing and classical computing to take advantage of quantum properties such as superposition, quantum entanglement, and Grover’s search algorithm to improve learning. Reinforcement Learning combines quantum-enhanced quantum function and quantum-based circuit to accelerate achievement and evaluate applications. We demonstrate experiments’ applicability, achievement, and scalability with state-of-the-art NLP problems: sentiment analysis, named entity recognition, and language modeling. The quantum enhanced learning model could deliver for practical applications fast learning and good accuracy in solving those problems than standard and quantum models.