FAST: Fidelity-Adjustable Semantic Transmission Over Heterogeneous Wireless Networks

In this work, we investigate the challenging problem of on-demand semantic communication over heterogeneous wireless networks. We propose a fidelity-adjustable semantic transmission framework (FAST) that empowers wireless devices to send data efficiently under different application scenarios and resource conditions. To this end, we first design a dynamic sub-model training scheme to learn the flexible semantic model, which enables edge devices to customize the transmission fidelity with different widths of the semantic model. After that, we focus on the FAST optimization problem to minimize the system energy consumption with latency and fidelity constraints. Following that, the optimal transmission strategies including the scaling factor of the semantic model, computing frequency, and transmitting power are derived for the devices. Experiment results indicate that, when compared to the baseline transmission schemes, the proposed framework can reduce up to one order of magnitude of the system energy consumption and data size for maintaining reasonable data fidelity.

I. Introduction

By 2030, 17.1 billion wireless devices equipped with versatile sensors will produce 5 zettabytes of data per month [1]. The explosive growth of edge-generated data rises challenges on how to achieve efficient information exchange among massive devices. Semantic communication is an emerging data transmission paradigm that aims to extract and deliver the explicative meaning of the data [2]. The semantic-aware communication systems can reveal the intrinsic information of the raw data by leveraging the knowledge of prior models [3], [4]. By integrating semantic communication into wireless networks, the required data traffic will be significantly reduced, leading to a green and reliable communication pattern [5], [6].