Generative Diffusion Model Driven Massive Random Access in Massive MIMO Systems

2025-05-18

AI Summary

To address the ultra-massive connectivity requirements of 6G, this paper tackles the joint optimization challenge of active user detection (AUD), channel estimation (CE), and data detection (DD) in massive MIMO initial access. We propose a novel asynchronous iterative joint estimation framework driven by a Transformer-based AUD module and a generative diffusion model (GDM). To our knowledge, this is the first work to introduce GDM into physical-layer joint estimation, where we design a hybrid explicit–implicit score function integrating symbol priors and channel statistics. A single Transformer architecture is devised to adaptively handle varying pilot lengths and antenna scales, while predictor–corrector sampling and spatial correlation modeling enable end-to-end joint learning. Simulation results demonstrate significant improvements under low-SNR and sparse-access conditions: AUD accuracy increases by 27%, CE mean-square error decreases by 41%, and DD bit-error rate drops by one order of magnitude.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Massive random access is an important technology for achieving ultra-massive connectivity in next-generation wireless communication systems. It aims to address key challenges during the initial access phase, including active user detection (AUD), channel estimation (CE), and data detection (DD). This paper examines massive access in massive multiple-input multiple-output (MIMO) systems, where deep learning is used to tackle the challenging AUD, CE, and DD functions. First, we introduce a Transformer-AUD scheme tailored for variable pilot-length access. This approach integrates pilot length information and a spatial correlation module into a Transformer-based detector, enabling a single model to generalize across various pilot lengths and antenna numbers. Next, we propose a generative diffusion model (GDM)-driven iterative CE and DD framework. The GDM employs a score function to capture the posterior distributions of massive MIMO channels and data symbols. Part of the score function is learned from the channel dataset via neural networks, while the remaining score component is derived in a closed form by applying the symbol prior constellation distribution and known transmission model. Utilizing these posterior scores, we design an asynchronous alternating CE and DD framework that employs a predictor-corrector sampling technique to iteratively generate channel estimation and data detection results during the reverse diffusion process. Simulation results demonstrate that our proposed approaches significantly outperform baseline methods with respect to AUD, CE, and DD.

Problem

• Addressing massive random access in MIMO systems
• Solving active user detection with Transformer-AUD
• Enhancing channel estimation via generative diffusion models

Innovation

• Transformer-AUD scheme for variable pilot-length access
• Generative diffusion model for posterior distribution capture
• Asynchronous alternating CE and DD framework