Variational Source-Channel Coding for Semantic Communication

2024-09-26

arXiv.org

AI Summary

Semantic communication suffers from weak interpretability, unclear performance limits, and insufficient theoretical justification for joint source–channel coding under conventional separation-based modeling. To address this, we propose the Variational Source–Channel Coding (VSCC) framework—a novel end-to-end trainable architecture that tightly couples variational inference with dynamic channel modeling via deep neural networks. VSCC fundamentally departs from Shannon’s separation theorem by theoretically proving the necessity of joint encoding for semantic communication and endowing latent variables with explicit statistical interpretations (e.g., variance). Experimentally, VSCC achieves superior semantic interpretability over standard autoencoders and enhanced semantic fidelity over VAEs at equivalent PSNR. Structural similarity (SSIM) evaluations further confirm that its reconstructions exhibit higher human readability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Visual Reasoning & Symbolic Representations

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: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Semantic communication technology emerges as a pivotal bridge connecting AI with classical communication. The current semantic communication systems are generally modeled as an Auto-Encoder (AE). AE lacks a deep integration of AI principles with communication strategies due to its inability to effectively capture channel dynamics. This gap makes it difficult to justify the need for joint source-channel coding (JSCC) and to explain why performance improves. This paper begins by exploring lossless and lossy communication, highlighting that the inclusion of data distortion distinguishes semantic communication from classical communication. It breaks the conditions for the separation theorem to hold and explains why the amount of data transferred by semantic communication is less. Therefore, employing JSCC becomes imperative for achieving optimal semantic communication. Moreover, a Variational Source-Channel Coding (VSCC) method is proposed for constructing semantic communication systems based on data distortion theory, integrating variational inference and channel characteristics. Using a deep learning network, we develop a semantic communication system employing the VSCC method and demonstrate its capability for semantic transmission. We also establish semantic communication systems of equivalent complexity employing the AE method and the VAE method. Experimental results reveal that the VSCC model offers superior interpretability compared to AE model, as it clearly captures the semantic features of the transmitted data, represented as the variance of latent variables in our experiments. In addition, VSCC model exhibits superior semantic transmission capabilities compared to VAE model. At the same level of data distortion evaluated by PSNR, VSCC model exhibits stronger human interpretability, which can be partially assessed by SSIM.

Problem

• Semantic communication lacks AI-communication integration in AE models
• JSCC is essential for optimal semantic communication performance
• VSCC method improves interpretability and transmission over AE/VAE

Innovation

• Proposes Variational Source-Channel Coding (VSCC) method
• Integrates variational inference with channel characteristics
• Enhances interpretability and semantic transmission capabilities