A Hybrid Quantum-Classical Autoencoder Framework for End-to-End Communication Systems

2024-12-28

IEEE Wireless Communications Letters

AI Summary

To address low spectral efficiency and high block error rates (BLER) caused by poor signal quality in wireless fading channels, this paper proposes a quantum-classical hybrid autoencoder architecture that couples parameterized quantum circuits with classical deep neural networks, enabling end-to-end differentiable joint source-channel coding optimization. For the first time in fading-channel communication systems, the method achieves BLER performance comparable to state-of-the-art classical DNNs and conventional coding schemes, while reducing trainable parameters by approximately 60% and accelerating BLER convergence with enhanced training stability. Key innovations include: (i) a task-oriented, lightweight hybrid quantum circuit design tailored for communication, and (ii) a channel-adaptive quantum-classical co-gradient optimization mechanism. This work establishes a novel paradigm for deploying quantum machine learning in practical wireless communication systems.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

This paper investigates the application of quantum machine learning to End-to-End (E2E) communication systems in wireless fading scenarios. We introduce a novel hybrid quantum-classical autoencoder architecture that combines parameterized quantum circuits with classical deep neural networks (DNNs). Specifically, we propose a hybrid quantum-classical autoencoder (QAE) framework to optimize the E2E communication system. Our results demonstrate the feasibility of the proposed hybrid system, and reveal that it is the first work that can achieve comparable block error rate (BLER) performance to classical DNN-based and conventional channel coding schemes, while significantly reducing the number of trainable parameters. Additionally, the proposed QAE exhibits steady and superior BLER convergence over the classical autoencoder baseline.

Problem

• Quantum Machine Learning
• Wireless Signal Quality
• Communication Efficiency

Innovation

• Quantum-Enhanced Autoencoder
• Hybrid Quantum-Traditional Circuit
• Wireless Signal Optimization