Deep Unfolding for MIMO Signal Detection

2025-07-23

AI Summary

Existing detection methods for massive MIMO systems rely on real-domain approximations, struggle with direct complex-valued signal processing, and suffer from high computational complexity. To address these limitations, this paper proposes a native complex-domain deep unfolding network. The method leverages Wirtinger calculus to formulate differentiable complex-valued gradient updates and introduces a novel dynamic partial shrinkage thresholding operator, enabling end-to-end learning directly in the complex domain. Furthermore, it adopts a lightweight network architecture that significantly reduces both the number of iterations and overall model complexity. Experimental results demonstrate that the proposed approach achieves superior detection accuracy compared to state-of-the-art real-domain and complex-domain baselines—under comparable or lower computational overhead. The method thus offers high efficiency, inherent interpretability, and hardware-friendly design, making it well-suited for real-time massive MIMO detection in 6G wireless systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• 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
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

In this paper, we propose a deep unfolding neural network-based MIMO detector that incorporates complex-valued computations using Wirtinger calculus. The method, referred as Dynamic Partially Shrinkage Thresholding (DPST), enables efficient, interpretable, and low-complexity MIMO signal detection. Unlike prior approaches that rely on real-valued approximations, our method operates natively in the complex domain, aligning with the fundamental nature of signal processing tasks. The proposed algorithm requires only a small number of trainable parameters, allowing for simplified training. Numerical results demonstrate that the proposed method achieves superior detection performance with fewer iterations and lower computational complexity, making it a practical solution for next-generation massive MIMO systems.

Problem

• Develops complex-valued deep unfolding MIMO detector
• Enables efficient interpretable low-complexity signal detection
• Improves performance with fewer iterations lower complexity

Innovation

• Deep unfolding network with Wirtinger calculus
• Dynamic Partially Shrinkage Thresholding (DPST)
• Native complex-domain low-parameter MIMO detection