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

Melek Krichen; Nikhitha Nunavath; Riccardo Bassoli; Soumaya Cherkaoui

Home/Archive/arXiv

arXiv · 2609.25044

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

Melek Krichen·Nikhitha Nunavath·Riccardo Bassoli·Soumaya Cherkaoui

View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

quant-ph cs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Melek Krichen, Nikhitha Nunavath, Riccardo Bassoli, Soumaya Cherkaoui. 2026-08-30. End-to-End Quantum Semantic Communication with Variational Quantum Neural Networks. https://arxiv.org/abs/2609.25044

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Bounded information as a foundation for quantum theory

The purpose of this paper is to formalize the concept that best synthesizes our intuitive understanding of quantum mechanics - that the information carried by a system is limited - and, from this principle, to construct the foundations of quantum theory. In our discussion, we also introduce a second important hypothesis: if a measurement closely approximates an ideal one in terms of experimental precision, the information it provides about a physical system is independent of the measurement method and, specifically, of the system's physical quantities being measured. This principle can be expressed in terms of metric properties of a manifold whose points represent the state of the system. These and other reasonable hypotheses provide the foundation for a framework of quantum reconstruction. The theory presented in this paper is based on a description of physical systems in terms of their statistical properties, specifically statistical parameters, and focuses on the study of estimators for these parameters. To achieve the goal of quantum reconstruction, a divide-and-conquer approach is employed, wherein the space of two discrete conjugate Hamiltonian variables is partitioned into a binary tree of nested sets. This approach naturally leads to the reconstruction of the linear and probabilistic structure of quantum mechanics.

quant-ph↗

arXiv2026

Reducibility of native weighted graphs on Rydberg Arrays

We investigate the classical reducibility of random unit-disk graph (UDG) instances of the maximum independent set (MIS) and maximum weighted independent set (MWIS) problems, which can be natively realised in Rydberg atom quantum processors. Using state-of-the-art kernelisation techniques, we systematically probe how far classical preprocessing can simplify such native optimisation problems of varying size and connectivity. While many small or sparse instances can be fully reduced, dense graphs often retain finite irreducible kernels even after extensive reductions. Introducing vertex weights tends to increase reducibility, whereas extending the interaction range in the underlying UDG connectivity suppresses the reduction efficiency. By exploring where classical reductions cease to be effective, we aim to delineate the regime of problem instances that remain computationally demanding - those most relevant for testing and benchmarking near-term quantum optimisation hardware. We find that for the remaining finite kernels, quantum execution would require non-native embeddings with substantial resource overheads, suggesting that directly running native instances may be more practical than embedding a reduced kernel.

quant-ph↗

arXiv2026

When Complementary Measurements Count the Same Classical Bit Twice: Counterexamples to CQC, ECQC, and Complementarity-Based Certification

Mutually unbiased measurements are commonly expected to expose independent facets of a quantum state: a correlation that is classical in one basis should disappear in a complementary basis. In higher dimensions, however, this intuition becomes particularly subtle because correlations recovered in different settings need not represent different information. To expose this loophole, we propose a two-branch classical null test: before the setting is chosen, a shared bit selects one of two orthogonal product preparations, producing a rank-two classical--classical state, and the candidate protocol then runs unchanged. Different settings can read the same bit through different outcome patterns. This two-branch classical architecture disproves the complementary-quantum correlation (CQC) conjecture in every dimension $d\geq3$. A distinct rank-two classical--classical state disproves its complete-basis extension (ECQC) at $d=7$, with an overrun that grows without bound along prime dimensions. Its qutrit CQC instance also gives classical false positives for a proposed quantum-correlation measure and a proposed one-sided semi-device-independent steering criterion, and refutes a conditional-probability conjecture. The failures identify the missing requirement: information read in different settings must be nonredundant. In experiments and applications, the same low-overhead architecture can serve as a calibration test before a multibasis score is assigned quantum meaning.

quant-ph↗