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:2609.25044

End-to-End Quantum Semantic Communication with Variational Quantum Neural Networks

Melek Krichen, Nikhitha Nunavath, Riccardo Bassoli, Soumaya Cherkaoui

quant-phcs.LGSubmitted Aug 30, 2026• Announced Sep 1, 2026• 0 citations
v1 · Aug 30, 2026v2 · Oct 6, 2026
arXivHTMLPDF

Abstract

This paper presents a quantum semantic communication (QSemCom) framework combining quantum machine learning (QML) and semantic communication (SemCom). Classical data are compressed into low-dimensional semantic representations, encoded and processed by a variational quantum transmitter, transmitted through a quantum channel, and processed by a trainable quantum receiver for classification. The framework considers a distributed quantum communication scenario in which quantum processing units (QPUs) exchange task-relevant semantic information through quantum links. While the general setting may involve multiple quantum nodes, this work focuses on the fundamental two-node case, with transmitter and receiver QPUs connected through a noisy quantum channel. Using MNIST, the framework is evaluated under ideal, bit-flip, depolarizing, and amplitude-damping channels. A baseline model is first trained over a perfect channel and evaluated under increasing noise without retraining. Receiver-side end-to-end training is then performed at fixed depolarizing-noise levels. The perfect-channel model achieves an accuracy of $0.9556$ and an F1-score of $0.9551$. Results show channel-dependent performance degradation, while receiver training substantially restores task performance under moderate and high depolarizing noise. Moreover, task recovery does not require reconstruction of the transmitted density matrix, highlighting a distinction between physical-state recovery and semantic-feature recovery. These results demonstrate that a trainable quantum receiver can recover task-relevant semantic information from noise-distorted quantum states and maintain high classification performance.

Related papers

Quantum Machine Learning-Based Efficient Channel Estimation for MISO Systems

MinHyeok Choi, Ki-Chang Tong, Yeong-Gyun Jung +3 more

Accurate channel estimation is a fundamental requirement for high-performance wireless communication systems, where conventional deep learning approaches often suffer from excessive trainable parameters and high memory cost as antenna and subcarrier dimensions scale up. This paper proposes a quantum machine learning (QML)-based channel estimation framework that addresses this scalability challenge through a compact hybrid quantum-classical architecture. An 8-qubit quantum neural network (QNN) based on a parameterized quantum circuit (PQC) encodes received pilot-domain features using both Cartesian and polar components through Hadamard initialization and rotation-based quantum encoding, and learns channel representations using trainable variational rotations and controlled-Z (CZ) entanglement. The Pauli-Z measurement outputs are then processed by a lightweight classical dense head to produce the final channel estimate. The proposed QNN is compared with a classical deep neural network (DNN) and a QNN without hidden dense layers over a 2 × 1 Rayleigh fading multiple-input single-output (MISO) channel across an SNR range of 10 dB to 30 dB. Simulation results show that the proposed hybrid QNN achieves the lowest normalized mean square error (NMSE) across the entire evaluated SNR range while using only 1,012 trainable parameters, compared with 3,356 for the DNN. At 30 dB SNR, the proposed QNN achieves the lowest NMSE of approximately − 20.24 dB, compared with approximately − 17.54 dB for the DNN baseline. An ablation study further confirms that the dense post-processing head is essential for accurate regression from raw quantum measurement outputs. These results suggest that compact hybrid quantum-classical estimators offer a promising direction for accurate and parameter-efficient channel estimation in next-generation wireless communication systems.

International Conference on Computer and Communications Management (ICCCM)•Jul 24, 2026•0 citations

QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks

Jun Qi, Chao-Han Huck Yang, Pin‐Yu Chen

The advent of noisy intermediate-scale quantum (NISQ) computers raises a crucial challenge to design quantum neural networks for fully quantum learning tasks. To bridge the gap, this work proposes an end-to-end learning framework named QTN-VQC, by introducing a trainable quantum tensor network (QTN) for quantum embedding on a variational quantum circuit (VQC). The architecture of QTN is composed of a parametric tensor-train network for feature extraction and a tensor product encoding for quantum embedding. We highlight the QTN for quantum embedding in terms of two perspectives: (1) we theoretically characterize QTN by analyzing its representation power of input features; (2) QTN enables an end-to-end parametric model pipeline, namely QTN-VQC, from the generation of quantum embedding to the output measurement. Our experiments on the MNIST dataset demonstrate the advantages of QTN for quantum embedding over other quantum embedding approaches.

arXiv:2110.03861•Oct 6, 2021•10 citations

Quantum Machine Learning for Classification Tasks:Variational Quantum Classifiers and Quantum Neural Networks

Dr K N S Lakshmi, Bondalapu Sandhya, Nasari Durga Prasad +2 more

Quantum Machine Learning (QML) has emerged as a compelling research domain that unites quantum computing principles with classical learning theory to address computationally demanding classification problems.This paper investigates two principal QML architectures-Variational Quantum Classifiers (VQC) and Quantum Neural Networks (QNN)-within the context of binary classification.We present an end-to-end hybrid quantum-classical pipeline applied to the UCI Mushroom dataset, comprising 22 categorical attributes, and demonstrate that quantumenhanced models can achieve competitive classification performance under present-day hardware constraints.The pipeline integrates Quantum Random Access Code (QRAC) encoding for dimensionality reduction, ZZFeatureMapbased quantum feature mapping, RealAmplitudes parameterized ansatz, and classical optimizer-driven parameter updates using the COBYLA algorithm.The complete system is deployed through a Flask web interface and containerized with Docker for reproducibility.Experimental results on a quantum simulator indicate a classification accuracy of 87.4%, precision of 0.891, and recall of 0.863, establishing the practical viability of NISQ-era quantum classifiers for structured categorical data.The paper further analyzes convergence behavior, circuit depth effects, and comparative performance against classical baselines, providing insights into the strengths and limitations of current QML architectures for real-world classification deployment.

Journal of Science Engineering Technology and Management Sciences•Mar 1, 2026•0 citations

Towards Quantum Semantic Communications: A Framework for Integrating Quantum and Semantic Technologies

Nikhitha Nunavath, Nour Hello, Emilio Calvanese Strinati +2 more

This paper explores integrating quantum technologies with semantic communications to address the challenges of transmitting knowledge graph embeddings over traditional communication channels. As communication systems evolve to facilitate knowledge sharing and processing among natural and artificial intelligent agents, they encounter issues such as inefficiency, inaccuracy, and high complexity. To address these challenges, we propose a novel approach called quantum semantic communications, which integrates quantum technologies into the emerging framework of semantic communications. The primary goal of this protocol is to transmit semantic features efficiently, minimizing resource consumption while ensuring robustness. Our approach involves extracting semantic data from knowledge graphs using pre-trained large language model encoder and graph neural network as semantic encoders to generate compact knowledge representations transmitted over quantum communication channels. To assess the effectiveness of our protocol, we analyze performance metrics such as quantum semantic fidelity and F1 score under various noise conditions, including depolarizing, amplitude damping, and dephasing. Our simulations show that the proposed quantum semantic communication approach remains robust even in a low signal-to-noise regime.

IEEE Globecom Workshops (GC Wkshps)•Dec 8, 2024•8 citations

Quantum Semantic Sensing Approach for Intelligent IoT

Nikhitha Nunavath, Riccardo Bassoli, Frank H. P. Fitzek

The exponential growth of IoT devices in future 6G networks necessitates a paradigm shift from traditional data-centric communication to semantically meaningful, goaloriented communication models that optimize information relevance, efficiency, and intent-driven exchange. In this work, we propose a novel quantum semantic sensing model that integrates semantic communication technologies with quantum mechanical principles for goal-oriented tasks. By leveraging quantum interference and quantum teleportation, our model enables goal-driven communication over noisy quantum links. To validate our theoretical framework, we implement the full pipeline using the NetSquid quantum network simulator. Instead of transmitting full sensor observations, our model semantically fuses taskrelevant embeddings into low-dimensional quantum states, encodes them for teleportation, and verifies alignment with receiver goals through quantum interference. The protocol's performance is evaluated using two baseline strategies: (i) quantum teleportation fidelity, and (ii) semantic fidelity i.e., the degree of semantic equivalence between sender and receiver assessed via quantum interference. Our results show that semantic fidelity remains above 0.8 even when teleportation fidelity drops below 0.6, confirming the hypothesis that exact quantum state reconstruction is not required for effective goaloriented semantic inference.

IEEE Middle East Conference on Communications and Networking (MECOM)•Nov 4, 2025•0 citations

Quantum Communication for Semantic Communication Based Image Transmission

Udara Jayasinghe, Prabhath Samarathunga, Nimesh Pollwaththage +2 more

The growing demand for reliable image transmission in noisy vehicular networks exposes the limitations of classical communication, which often suffers from bandwidth constraints and susceptibility to noise. Classical semantic communication addresses this by focusing on essential information, but it still struggles to maintain consistent image quality under adverse channel conditions. To address these limitations, this study proposes a quantum communication system for semantic communication-based image transmission by leveraging quantum superposition. The system first uses a semantic encoder to generate a compact latent representation. This representation is subsequently processed by a channel encoder and mapped into quantum superposition states using a quantum encoder. The resulting quantum states are sent through a noisy quantum channel, where they are measured and decoded at the receiver to recover the corresponding classical bitstream. The bitstream is then channel decoded to recover the latent vector, which is used by a semantic decoder to reconstruct the image. Results from the experiments confirm that the proposed system outperforms classical semantic communication systems, achieving a peak signal-to-noise ratio (PSNR) of up to 28.55 dB, a structural similarity index (SSIM) of up to 0.7996, a universal quality index (UQI) of up to 0.7836, and perfect classification accuracy at channel SNR levels as low as 6 dB, as evaluated by a convolutional neural network (CNN). These results highlight the system's effectiveness in task-oriented communication and show that combining quantum and semantic communication enhances image quality and reliability in challenging vehicular scenarios.

IEEE Transactions on Vehicular Technology•Feb 11, 2026•3 citations
This paper presents a quantum semantic communication (QSemCom) framework combining quantum machine learning (QML) and semantic communication (SemCom). Classical data are compressed into low-dimensional semantic representations, encoded and processed by a variational quantum transmitter, transmitted through a quantum channel, and processed by a trainable quantum receiver for classification. The framework considers a distributed quantum communication scenario in which quantum processing units (QPUs) exchange task-relevant semantic information through quantum links. While the general setting may involve multiple quantum nodes, this work focuses on the fundamental two-node case, with transmitter and receiver QPUs connected through a noisy quantum channel. Using MNIST, the framework is evaluated under ideal, bit-flip, depolarizing, and amplitude-damping channels. A baseline model is first trained over a perfect channel and evaluated under increasing noise without retraining. Receiver-side end-to-end training is then performed at fixed depolarizing-noise levels. The perfect-channel model achieves an accuracy of 0.95560.95560.9556 and an F1-score of 0.95510.95510.9551. Results show channel-dependent performance degradation, while receiver training substantially restores task performance under moderate and high depolarizing noise. Moreover, task recovery does not require reconstruction of the transmitted density matrix, highlighting a distinction between physical-state recovery and semantic-feature recovery. These results demonstrate that a trainable quantum receiver can recover task-relevant semantic information from noise-distorted quantum states and maintain high classification performance.
Accurate channel estimation is a fundamental requirement for high-performance wireless communication systems, where conventional deep learning approaches often suffer from excessive trainable parameters and high memory cost as antenna and subcarrier dimensions scale up. This paper proposes a quantum machine learning (QML)-based channel estimation framework that addresses this scalability challenge through a compact hybrid quantum-classical architecture. An 8-qubit quantum neural network (QNN) based on a parameterized quantum circuit (PQC) encodes received pilot-domain features using both Cartesian and polar components through Hadamard initialization and rotation-based quantum encoding, and learns channel representations using trainable variational rotations and controlled-Z (CZ) entanglement. The Pauli-Z measurement outputs are then processed by a lightweight classical dense head to produce the final channel estimate. The proposed QNN is compared with a classical deep neural network (DNN) and a QNN without hidden dense layers over a 2 × 1 Rayleigh fading multiple-input single-output (MISO) channel across an SNR range of 10 dB to 30 dB. Simulation results show that the proposed hybrid QNN achieves the lowest normalized mean square error (NMSE) across the entire evaluated SNR range while using only 1,012 trainable parameters, compared with 3,356 for the DNN. At 30 dB SNR, the proposed QNN achieves the lowest NMSE of approximately − 20.24 dB, compared with approximately − 17.54 dB for the DNN baseline. An ablation study further confirms that the dense post-processing head is essential for accurate regression from raw quantum measurement outputs. These results suggest that compact hybrid quantum-classical estimators offer a promising direction for accurate and parameter-efficient channel estimation in next-generation wireless communication systems.
The advent of noisy intermediate-scale quantum (NISQ) computers raises a crucial challenge to design quantum neural networks for fully quantum learning tasks. To bridge the gap, this work proposes an end-to-end learning framework named QTN-VQC, by introducing a trainable quantum tensor network (QTN) for quantum embedding on a variational quantum circuit (VQC). The architecture of QTN is composed of a parametric tensor-train network for feature extraction and a tensor product encoding for quantum embedding. We highlight the QTN for quantum embedding in terms of two perspectives: (1) we theoretically characterize QTN by analyzing its representation power of input features; (2) QTN enables an end-to-end parametric model pipeline, namely QTN-VQC, from the generation of quantum embedding to the output measurement. Our experiments on the MNIST dataset demonstrate the advantages of QTN for quantum embedding over other quantum embedding approaches.
Quantum Machine Learning (QML) has emerged as a compelling research domain that unites quantum computing principles with classical learning theory to address computationally demanding classification problems.This paper investigates two principal QML architectures-Variational Quantum Classifiers (VQC) and Quantum Neural Networks (QNN)-within the context of binary classification.We present an end-to-end hybrid quantum-classical pipeline applied to the UCI Mushroom dataset, comprising 22 categorical attributes, and demonstrate that quantumenhanced models can achieve competitive classification performance under present-day hardware constraints.The pipeline integrates Quantum Random Access Code (QRAC) encoding for dimensionality reduction, ZZFeatureMapbased quantum feature mapping, RealAmplitudes parameterized ansatz, and classical optimizer-driven parameter updates using the COBYLA algorithm.The complete system is deployed through a Flask web interface and containerized with Docker for reproducibility.Experimental results on a quantum simulator indicate a classification accuracy of 87.4%, precision of 0.891, and recall of 0.863, establishing the practical viability of NISQ-era quantum classifiers for structured categorical data.The paper further analyzes convergence behavior, circuit depth effects, and comparative performance against classical baselines, providing insights into the strengths and limitations of current QML architectures for real-world classification deployment.
This paper explores integrating quantum technologies with semantic communications to address the challenges of transmitting knowledge graph embeddings over traditional communication channels. As communication systems evolve to facilitate knowledge sharing and processing among natural and artificial intelligent agents, they encounter issues such as inefficiency, inaccuracy, and high complexity. To address these challenges, we propose a novel approach called quantum semantic communications, which integrates quantum technologies into the emerging framework of semantic communications. The primary goal of this protocol is to transmit semantic features efficiently, minimizing resource consumption while ensuring robustness. Our approach involves extracting semantic data from knowledge graphs using pre-trained large language model encoder and graph neural network as semantic encoders to generate compact knowledge representations transmitted over quantum communication channels. To assess the effectiveness of our protocol, we analyze performance metrics such as quantum semantic fidelity and F1 score under various noise conditions, including depolarizing, amplitude damping, and dephasing. Our simulations show that the proposed quantum semantic communication approach remains robust even in a low signal-to-noise regime.
The exponential growth of IoT devices in future 6G networks necessitates a paradigm shift from traditional data-centric communication to semantically meaningful, goaloriented communication models that optimize information relevance, efficiency, and intent-driven exchange. In this work, we propose a novel quantum semantic sensing model that integrates semantic communication technologies with quantum mechanical principles for goal-oriented tasks. By leveraging quantum interference and quantum teleportation, our model enables goal-driven communication over noisy quantum links. To validate our theoretical framework, we implement the full pipeline using the NetSquid quantum network simulator. Instead of transmitting full sensor observations, our model semantically fuses taskrelevant embeddings into low-dimensional quantum states, encodes them for teleportation, and verifies alignment with receiver goals through quantum interference. The protocol's performance is evaluated using two baseline strategies: (i) quantum teleportation fidelity, and (ii) semantic fidelity i.e., the degree of semantic equivalence between sender and receiver assessed via quantum interference. Our results show that semantic fidelity remains above 0.8 even when teleportation fidelity drops below 0.6, confirming the hypothesis that exact quantum state reconstruction is not required for effective goaloriented semantic inference.
The growing demand for reliable image transmission in noisy vehicular networks exposes the limitations of classical communication, which often suffers from bandwidth constraints and susceptibility to noise. Classical semantic communication addresses this by focusing on essential information, but it still struggles to maintain consistent image quality under adverse channel conditions. To address these limitations, this study proposes a quantum communication system for semantic communication-based image transmission by leveraging quantum superposition. The system first uses a semantic encoder to generate a compact latent representation. This representation is subsequently processed by a channel encoder and mapped into quantum superposition states using a quantum encoder. The resulting quantum states are sent through a noisy quantum channel, where they are measured and decoded at the receiver to recover the corresponding classical bitstream. The bitstream is then channel decoded to recover the latent vector, which is used by a semantic decoder to reconstruct the image. Results from the experiments confirm that the proposed system outperforms classical semantic communication systems, achieving a peak signal-to-noise ratio (PSNR) of up to 28.55 dB, a structural similarity index (SSIM) of up to 0.7996, a universal quality index (UQI) of up to 0.7836, and perfect classification accuracy at channel SNR levels as low as 6 dB, as evaluated by a convolutional neural network (CNN). These results highlight the system's effectiveness in task-oriented communication and show that combining quantum and semantic communication enhances image quality and reliability in challenging vehicular scenarios.