Cache-enabled Generative Joint Source-Channel Coding for Evolving Semantic Communications

2026-03-18

AI Summary

This work addresses the limitations of existing semantic communication methods, which rely on end-to-end training, struggle to adapt to dynamic channels, and overlook semantic redundancy across transmissions, thereby constraining efficiency. To overcome these challenges, the paper proposes a training-free semantic communication framework that uniquely integrates a pretrained generative model with a semantic-level caching mechanism. Specifically, it employs a channel-aware SemanticStyleGAN inversion for joint source-channel coding, decouples and caches previously transmitted semantic components to reuse redundant content, and dynamically constructs a codebook to enhance adaptability. Evaluated on image transmission, the method achieves an average bandwidth compression ratio of 1/224 (as low as 1/1024), substantially outperforming the 1/128 baseline while maintaining comparable perceptual quality.

Technology Category

• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Multiagent Systems: Agent Communication

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: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Learning-based semantic communication (SemCom) has recently emerged as a promising paradigm for improving the transmission efficiency of wireless networks. However, existing methods typically rely on extensive end-to-end training, which is both inflexible and computationally expensive in dynamic wireless environments. Moreover, they fail to exploit redundancy across multiple transmissions of semantically similar content, limiting overall efficiency. To overcome these limitations, we propose a channel-aware generative adversarial network (GAN) inversion-based joint source-channel coding (CAGI-JSCC) framework that enables training-free SemCom by leveraging a pre-trained SemanticStyleGAN model. By explicitly incorporating wireless channel characteristics into the GAN inversion process, CAGI-JSCC adapts to varying channel conditions without additional training. Furthermore, we introduce a cache-enabled dynamic codebook (CDC) that caches disentangled semantic components at both the transmitter and receiver, allowing the system to reuse previously transmitted content. This semantic-level caching can continuously reduce redundant transmissions as experience accumulates. Extensive experiments on image transmission demonstrate the effectiveness of the proposed framework. In particular, our system achieves comparable perceptual quality with an average bandwidth compression ratio (BCR) of 1/224, and as low as 1/1024 for a single image, significantly outperforming baselines with a BCR of 1/128.

Problem

• semantic communication
• joint source-channel coding
• wireless networks
• redundancy exploitation
• dynamic environments

Innovation

• semantic communication
• GAN inversion
• cache-enabled
• joint source-channel coding
• training-free