Iterative Gaussian Approximation for Random Spreading Unsourced Random Access

2025-12-19

AI Summary

In massive machine-type communication (mMTC) scenarios, random access (RA) schemes based on sparse code multiple access (SCMA) or related random-spread unsourced RA (RS-URA) suffer from degraded decoding performance and high computational complexity under low active-user loads. To address this, this paper proposes a generic iterative Gaussian approximation (IGA) decoding framework. The framework integrates message passing with nested inner–outer soft-information updates, requires no channel prior knowledge, and supports arbitrary random spreading codebooks. Its key innovation lies in establishing the first generalizable, low-complexity Gaussian approximation iterative paradigm, achieving rapid convergence—within 3–5 iterations—to near-theoretic performance limits. Experimental results demonstrate that, under low-SNR and sparse-activation conditions, the proposed method reduces packet error rate (PER) by 2–3 dB compared to state-of-the-art approaches, significantly enhancing robustness and practical applicability.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Information Theory

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Massive machine-type communications (mMTC) demand robust solutions to support extensive connectivity efficiently. Unsourced random access (URA) has emerged as a promising approach, delivering high spectral and energy efficiency. Among URA code structures, the random spreading (RS) category is a key enabler, providing strong anti-interference capabilities through spectrum spreading gain. Notably, RS-URA approaches theoretical performance limits over the Gaussian multiple access channel in scenarios with few active users. In this paper, we propose an iterative Gaussian approximation decoder designed universally for RS-URA categories. The proposed receiver iterates extrinsic and intrinsic soft information to enhance decoding performance, requiring only a few iterations to converge. Numerical results validate the decoder's effectiveness in terms of performance and robustness.

Problem

• Develops a decoder for unsourced random access with random spreading
• Enhances decoding performance using iterative Gaussian approximation
• Improves robustness and efficiency in massive machine-type communications

Innovation

• Iterative Gaussian approximation decoder for RS-URA
• Extrinsic and intrinsic soft information iteration
• Few iterations for convergence and robustness