Channel-Aware Vector Quantization for Robust Semantic Communication on Discrete Channels

2025-10-21

AI Summary

Poor compatibility of semantic communication with modern digital infrastructure, coupled with the robustness deficiency of existing vector quantization methods that ignore channel state information (CSI), motivates this work. We propose a channel-aware discrete semantic communication framework. Its core innovations are: (i) explicit incorporation of CSI into codebook optimization, and (ii) a multi-codebook alignment mechanism to resolve index-to-modulation-symbol ordering mismatches; and (iii) a joint source-channel coding architecture enabling end-to-end discrete mapping from semantic features to modulation symbols. Modeling the channel as a discrete memoryless channel and leveraging vector quantization, our method significantly mitigates the “digital cliff effect.” Experimental results demonstrate consistent improvements over baseline approaches across multiple digital modulation schemes—achieving 1.8–3.2 dB PSNR gains in reconstruction quality, enhanced noise robustness, and improved spectral efficiency.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Deep learning-based semantic communication has largely relied on analog or semi-digital transmission, which limits compatibility with modern digital communication infrastructures. Recent studies have employed vector quantization (VQ) to enable discrete semantic transmission, yet existing methods neglect channel state information during codebook optimization, leading to suboptimal robustness. To bridge this gap, we propose a channel-aware vector quantization (CAVQ) algorithm within a joint source-channel coding (JSCC) framework, termed VQJSCC, established on a discrete memoryless channel. In this framework, semantic features are discretized and directly mapped to modulation constellation symbols, while CAVQ integrates channel transition probabilities into the quantization process, aligning easily confused symbols with semantically similar codewords. A multi-codebook alignment mechanism is further introduced to handle mismatches between codebook order and modulation order by decomposing the transmission stream into multiple independently optimized subchannels. Experimental results demonstrate that VQJSCC effectively mitigates the digital cliff effect, achieves superior reconstruction quality across various modulation schemes, and outperforms state-of-the-art digital semantic communication baselines in both robustness and efficiency.

Problem

• Enabling robust semantic communication over discrete channels
• Integrating channel awareness into vector quantization optimization
• Overcoming codebook-modulation order mismatches in digital transmission

Innovation

• Channel-aware vector quantization integrates channel transition probabilities
• Multi-codebook alignment handles codebook-modulation order mismatches
• Discrete semantic features directly map to modulation symbols