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

TL;DR

Experimental results demonstrate that the DM-MIMO effectively reduces the mean square errors of the equalized signal and the DM-MIMO semantic communication system (DM-MIMO-JSCC) outperforms the JSCC-based semantic communication system in image reconstruction.

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.

Figures (6)

• Figure 1: Architecture of DM-MIMO-JSCC.
• Figure 2: Probability density of ${\lambda_i}$$(i\in \{1,2\})$ in $2\times 2$ MIMO.
• Figure 3: The $t$-th sample step of DM-MIMO joint sampling algorithm.
• Figure 4: MSE performance versus SNR under $2\times2$ MIMO channel. CBR is set to $1/128$.
• Figure 5: PSNR performance versus SNR under $2\times2$ MIMO channel. CBR is set to $1/128$.