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

TL;DR

This paper introduces a training-free semantic communication framework using GAN inversion and semantic caching, significantly improving transmission efficiency and adaptability in dynamic wireless environments.

Contribution

It proposes a novel cache-enabled GAN-based joint source-channel coding method that adapts to channel variations without retraining and reduces redundancy through semantic caching.

Findings

Achieves high perceptual quality at very high compression ratios.

Outperforms baseline methods in bandwidth efficiency.

Demonstrates effective adaptation to changing channel conditions.

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.