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

Engineering Applications of Artificial Intelligence

Genetic algorithm-enhanced neural network for parameter optimization of quantum key distribution

Haonan Ying, Jihao Fan

Published Oct 1, 2026• 0 citations
Publisher
DOI
10.1016/j.engappai.2026.116395

Related papers

Can quantum genetic algorithm really improve quantum backpropagation neural network?

Il-Hyang Choe, Gwang-Jin Kim, Nam-Chol Kim +5 more

Quantum Information Processing•Mar 22, 2023•9 citations

Machine learning with neural networks for parameter optimization in twin-field quantum key distribution

Jia-Le Kang, Minghui Zhang, Xiaopeng Liu +1 more

Quantum Information Processing•Aug 16, 2023•10 citations

An Enhanced Algorithm Framework for Optimizing Quantum Key Distribution Parameters

Haonan Ying, Jihao Fan

Quantum key distribution (QKD) parameter optimization is crucial for maximizing secure key rates. However, the commonly used Local Search Algorithm (LSA) exhibits significant limitations in certain protocols due to non-convexity or excessively narrow parameter spaces. To address this, neural network-based approaches have been proposed to shift the computational burden offline, enabling rapid parameter prediction at runtime without repeated optimization. This paper proposes a neural network framework incorporating genetic algorithms (GA) for QKD parameter optimization. We develop a customized GA to generate high-quality training data and employ a multi-head residual neural network. To rigorously evaluate the impact of the optimization algorithm on learning performance, we train separate models using datasets generated by GA and LSA, respectively. Experimental validation demonstrates that GA-based models achieve substantial performance gains, yielding higher$R^{2}$and significantly reducing prediction errors (RMSE and MAE) compared to LSA-based models for both symmetric and asymmetric BB84 protocols.

Information Communication Technologies Conference (ICTC)•May 1, 2026•0 citations

Parameter Optimization of Continuous-Variable Quantum Key Distribution Based on Ga-Bp Neural Network

Na Wang, Weicheng Yu, Xueqin Jiang +3 more

In the continuous-variable quantum key distribution (CV-QKD) system, the secret key rate (SKR) and transmission distance are important factors to evaluate the quality of system. Numerical methods are commonly employed to compute SKR of QKD systems in practice, but it is difficult to find the optimal parameter to enhance SKR. In this paper, we propose a machine learning-based parameter optimization scheme of CV-QKD. The proposed scheme applies the genetic algorithm-back propagation neural network (GA-BPNN) to CV-QKD to learn the mapping relationship between SKR and modulation variance. According to the property that the mapping relationship is a concave function, the optimal modulation variance can be determined by bisection, and then SKR can be enhanced. Simulation results demonstrate that the proposed scheme can enhance SKR and transmission distance.

International Conference on Communications, Circuits and Systems•May 23, 2025•1 citation

Multi-layer quantum neural network controller trained by real-coded genetic algorithm

Kazuhiko Takahashi, Motoki Kurokawa, Masafumi Hashimoto

Neurocomputing•Jan 29, 2014•37 citations

Quantum‐Enhanced Genetic Algorithm for Quantum Neural Network Optimization

Kehan Chen, Yixi Wei, Fei Yan

ABSTRACT This work proposes a Quantum Enhanced Genetic Algorithm (QEGA) that synergistically integrates three quantum‐inspired operators: a Grover adaptive search‐based selection mechanism, a swap test‐guided crossover scheme, and a quantum walk‐driven mutation process. By harnessing quantum amplitude amplification, entanglement recombination, and probabilistic exploration, QEGA pioneers the integration of quantum computational advantages into evolutionary optimization for quantum neural network parameters. The algorithm enhances global search effectiveness while accelerating convergence and exhibiting robust resistance to local optima. Experimental results on three benchmark datasets, i.e., Iris, the plane point set, and MNIST binary classification, demonstrate that QEGA outperforms classical genetic algorithms and quantum optimization algorithms from recent studies by a substantial margin on classification tasks. Specifically, it attains a peak accuracy of 98.67%, 99.16%, and 98.00% on the three datasets, respectively, accompanied by consistently smooth and monotonic convergence behaviors across the evaluated trials. These findings validate QEGA's potential as a versatile optimization framework for quantum neural network training and highlight the broader promise of quantum‐enhanced evolutionary computation in practical machine learning applications.

Advanced Quantum Technologies•Aug 1, 2026•0 citations
Quantum key distribution (QKD) parameter optimization is crucial for maximizing secure key rates. However, the commonly used Local Search Algorithm (LSA) exhibits significant limitations in certain protocols due to non-convexity or excessively narrow parameter spaces. To address this, neural network-based approaches have been proposed to shift the computational burden offline, enabling rapid parameter prediction at runtime without repeated optimization. This paper proposes a neural network framework incorporating genetic algorithms (GA) for QKD parameter optimization. We develop a customized GA to generate high-quality training data and employ a multi-head residual neural network. To rigorously evaluate the impact of the optimization algorithm on learning performance, we train separate models using datasets generated by GA and LSA, respectively. Experimental validation demonstrates that GA-based models achieve substantial performance gains, yielding higherR2R^{2}R2and significantly reducing prediction errors (RMSE and MAE) compared to LSA-based models for both symmetric and asymmetric BB84 protocols.
In the continuous-variable quantum key distribution (CV-QKD) system, the secret key rate (SKR) and transmission distance are important factors to evaluate the quality of system. Numerical methods are commonly employed to compute SKR of QKD systems in practice, but it is difficult to find the optimal parameter to enhance SKR. In this paper, we propose a machine learning-based parameter optimization scheme of CV-QKD. The proposed scheme applies the genetic algorithm-back propagation neural network (GA-BPNN) to CV-QKD to learn the mapping relationship between SKR and modulation variance. According to the property that the mapping relationship is a concave function, the optimal modulation variance can be determined by bisection, and then SKR can be enhanced. Simulation results demonstrate that the proposed scheme can enhance SKR and transmission distance.
ABSTRACT This work proposes a Quantum Enhanced Genetic Algorithm (QEGA) that synergistically integrates three quantum‐inspired operators: a Grover adaptive search‐based selection mechanism, a swap test‐guided crossover scheme, and a quantum walk‐driven mutation process. By harnessing quantum amplitude amplification, entanglement recombination, and probabilistic exploration, QEGA pioneers the integration of quantum computational advantages into evolutionary optimization for quantum neural network parameters. The algorithm enhances global search effectiveness while accelerating convergence and exhibiting robust resistance to local optima. Experimental results on three benchmark datasets, i.e., Iris, the plane point set, and MNIST binary classification, demonstrate that QEGA outperforms classical genetic algorithms and quantum optimization algorithms from recent studies by a substantial margin on classification tasks. Specifically, it attains a peak accuracy of 98.67%, 99.16%, and 98.00% on the three datasets, respectively, accompanied by consistently smooth and monotonic convergence behaviors across the evaluated trials. These findings validate QEGA's potential as a versatile optimization framework for quantum neural network training and highlight the broader promise of quantum‐enhanced evolutionary computation in practical machine learning applications.