DM-MIMO: Diffusion Models for Robust Semantic Communications over MIMO Channels

TL;DR

This paper introduces DM-MIMO, a diffusion model-based approach for robust semantic communication over MIMO channels, improving noise reduction and image reconstruction by learning signal distributions.

Contribution

It develops a diffusion model integrated with SVD-based processing for MIMO channels, enhancing robustness and performance in semantic communications.

Findings

DM-MIMO reduces mean square errors in signal equalization.

DM-MIMO outperforms JSCC-based systems in image reconstruction.

The joint sampling algorithm adapts to sub-channel noise variations.

Abstract

This paper investigates robust semantic communications over multiple-input multiple-output (MIMO) fading channels. Current semantic communications over MIMO channels mainly focus on channel adaptive encoding and decoding, which lacks exploration of signal distribution. To leverage the potential of signal distribution in signal space denoising, we develop a diffusion model over MIMO channels (DM-MIMO), a plugin module at the receiver side in conjunction with singular value decomposition (SVD) based precoding and equalization. Specifically, due to the significant variations in effective noise power over distinct sub-channels, we determine the effective sampling steps accordingly and devise a joint sampling algorithm. Utilizing a three-stage training algorithm, DM-MIMO learns the distribution of the encoded signal, which enables noise elimination over all sub-channels. Experimental results demonstrate that the DM-MIMO effectively reduces the mean square errors (MSE) of the equalized signal and the DM-MIMO semantic communication system (DM-MIMO-JSCC) outperforms the JSCC-based semantic communication system in image reconstruction.