Scalable Multi-Task Semantic Communication System with Feature Importance Ranking
Jiangjing Hu, Fengyu Wang, Wenjun Xu, Hui Gao, Ping Zhang
Abstract
Semantic communications are expected to be an innovative solution to the emerging intelligent applications in the era of connected intelligence. In this paper, a novel scalable multi-task semantic communication system with feature importance ranking (SMSC-FIR) is explored. Firstly, the multi-task correlations are investigated by a joint semantic encoder to extract relevant features. Then, a new scalable coding method is proposed based on feature importance ranking, which dynamically adjusts the coding rate and guarantees that important features for semantic tasks are transmitted with higher priority. Simulation results show that SMSC-FIR achieves performance gain w.r.t. individual intelligent tasks, especially in the low SNR regime.
BibTeX
@inproceedings{icassp2023_scalablemultitas,
title = {Scalable Multi-Task Semantic Communication System with Feature Importance Ranking},
author = {Jiangjing Hu and Fengyu Wang and Wenjun Xu and Hui Gao and Ping Zhang},
booktitle = {ICASSP 2023},
year = {2023}
}