Residual Diffusion Models for Variable-Rate Joint Source Channel Coding of MIMO CSI

2025-05-27

AI Summary

To address the performance degradation of joint source-channel coding (JSCC) under finite blocklengths and adverse channel conditions, this paper proposes a lightweight autoencoder–residual diffusion collaborative iterative reconstruction framework. Departing from conventional separated coding and existing autoencoder-based JSCC approaches, we introduce the first residual diffusion-enhanced JSCC architecture, integrating dynamic channel-aware decoding, parameterized variable-rate design, and quantization-robust mechanisms. The framework enables single-model multi-rate operation, two-stage low-latency inference, and robustness to channel estimation mismatch. Experimental results on typical MIMO scenarios demonstrate that the proposed method significantly outperforms state-of-the-art autoencoder-based JSCC schemes, achieving PSNR gains of 3.2–5.8 dB while reducing model parameters by 40%. It thus offers superior reconstruction fidelity, low computational overhead, and strong generalization capability across diverse channel conditions.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Despite significant advancements in deep learning-based CSI compression, some key limitations remain unaddressed. Current approaches predominantly treat CSI compression as a source coding problem, neglecting transmission errors. In finite block length regimes, separate source and channel coding proves suboptimal, with reconstruction performance deteriorating significantly under challenging channel conditions. While existing autoencoder-based compression schemes can be readily extended to support joint source-channel coding, they struggle to capture complex channel distributions and exhibit poor scalability with increasing parameter count. To overcome these inherent limitations of autoencoder-based approaches, we propose Residual-Diffusion Joint Source-Channel Coding (RD-JSCC), a novel framework that integrates a lightweight autoencoder with a residual diffusion module to iteratively refine CSI reconstruction. Our flexible decoding strategy balances computational efficiency and performance by dynamically switching between low-complexity autoencoder decoding and sophisticated diffusion-based refinement based on channel conditions. Comprehensive simulations demonstrate that RD-JSCC significantly outperforms existing autoencoder-based approaches in challenging wireless environments. Furthermore, RD-JSCC offers several practical features, including a low-latency 2-step diffusion during inference, support for multiple compression rates with a single model, robustness to fixed-bit quantization, and adaptability to imperfect channel estimation.

Problem

• Addresses limitations in deep learning-based CSI compression
• Improves reconstruction under challenging channel conditions
• Enhances scalability and robustness in wireless environments

Innovation

• Integrates autoencoder with residual diffusion module
• Dynamic switching between decoding strategies
• Supports multiple compression rates with single model