Hybrid Quantum Convolutional Neural Network-Aided Pilot Assignment in Cell-Free Massive MIMO Systems

2025-07-09

AI Summary

To address the high computational complexity and low convergence efficiency caused by pilot allocation in cell-free massive MIMO systems, this paper proposes a quantum-classical hybrid architecture: a lightweight Hybrid Quantum Convolutional Neural Network (HQ-CNN), which embeds a parameterized quantum circuit into a classical convolutional neural network. The quantum circuit enables efficient enhancement and compression of high-dimensional channel features, while parameter sharing across quantum layers substantially reduces model degrees of freedom and training overhead, enabling end-to-end joint optimization. Experimental results demonstrate that the proposed HQ-CNN achieves ergodic sum throughput close to that of exhaustive search, significantly outperforming state-of-the-art methods. Moreover, it reduces training iterations by approximately 40%, effectively balancing performance, computational efficiency, and scalability.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

A sophisticated hybrid quantum convolutional neural network (HQCNN) is conceived for handling the pilot assignment task in cell-free massive MIMO systems, while maximizing the total ergodic sum throughput. The existing model-based solutions found in the literature are inefficient and/or computationally demanding. Similarly, conventional deep neural networks may struggle in the face of high-dimensional inputs, require complex architectures, and their convergence is slow due to training numerous hyperparameters. The proposed HQCNN leverages parameterized quantum circuits (PQCs) relying on superposition for enhanced feature extraction. Specifically, we exploit the same PQC across all the convolutional layers for customizing the neural network and for accelerating the convergence. Our numerical results demonstrate that the proposed HQCNN offers a total network throughput close to that of the excessive-complexity exhaustive search and outperforms the state-of-the-art benchmarks.

Problem

• Hybrid quantum CNN for pilot assignment in cell-free MIMO
• Overcome inefficiency of model-based and deep learning methods
• Maximize ergodic sum throughput with quantum-enhanced feature extraction

Innovation

• Hybrid quantum convolutional neural network for pilot assignment
• Parameterized quantum circuits enhance feature extraction
• Same PQC across layers accelerates convergence