Enabling Training-Free Semantic Communication Systems with Generative Diffusion Models

TL;DR

This paper introduces a training-free semantic communication system using generative diffusion models, which enhances robustness and performance without the need for large datasets or training under specific channel conditions.

Contribution

It proposes a novel diffusion model-based semantic encoding and decoding method that operates training-free and improves robustness against channel noise.

Findings

Outperforms baseline SemCom systems in simulations

Demonstrates robustness against channel noise

Validates effectiveness on Kodak dataset

Abstract

Semantic communication (SemCom) has recently emerged as a promising paradigm for next-generation wireless systems. Empowered by advanced artificial intelligence (AI) technologies, SemCom has achieved significant improvements in transmission quality and efficiency. However, existing SemCom systems either rely on training over large datasets and specific channel conditions or suffer from performance degradation under channel noise when operating in a training-free manner. To address these issues, we explore the use of generative diffusion models (GDMs) as training-free SemCom systems. Specifically, we design a semantic encoding and decoding method based on the inversion and sampling process of the denoising diffusion implicit model (DDIM), which introduces a two-stage forward diffusion process, split between the transmitter and receiver to enhance robustness against channel noise. Moreover, we optimize sampling steps to compensate for the increased noise level caused by channel noise. We also conduct a brief analysis to provide insights about this design. Simulations on the Kodak dataset validate that the proposed system outperforms the existing baseline SemCom systems across various metrics.