Importance-Aware Semantic Communication in MIMO-OFDM Systems Using Vision Transformer

TL;DR

This paper introduces an importance-aware semantic communication framework for MIMO-OFDM systems that leverages Vision Transformer attention to optimize resource allocation, improving task accuracy and efficiency under practical transmission constraints.

Contribution

It proposes a novel IA-QSMPA framework that jointly optimizes quantization, subcarrier mapping, and power allocation using ViT-based importance, extending to finite blocklength scenarios with an efficient optimization method.

Findings

Significantly outperforms conventional methods in simulations.

Achieves better task performance and communication efficiency.

Effective under both ideal and finite blocklength transmission conditions.

Abstract

This paper presents a novel importance-aware quantization, subcarrier mapping, and power allocation (IA-QSMPA) framework for semantic communication in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, empowered by a pretrained Vision Transformer (ViT). The proposed framework exploits attention-based importance extracted from a pretrained ViT to jointly optimize quantization levels, subcarrier mapping, and power allocation. Specifically, IA-QSMPA maps semantically important features to high-quality subchannels and allocates resources in accordance with their contribution to task performance and communication latency. To efficiently solve the resulting nonconvex optimization problem, a block coordinate descent algorithm is employed. The framework is further extended to operate under finite blocklength transmission, where communication errors may occur. In this setting, a segment-wise linear approximation of the channel dispersion penalty is introduced to enable efficient joint optimization under practical constraints. Simulation results on a multi-view image classification task using the MVP-N dataset demonstrate that IA-QSMPA significantly outperforms conventional methods in both ideal and finite blocklength transmission scenarios, achieving superior task performance and communication efficiency.