Intellicise model transmission for semantic communication in intelligence-native 6G networks

To facilitate emerging applications and demands of edge intelligence (EI)-empowered 6G networks, model-driven semantic communications have been proposed to reduce transmission volume by deploying artificial intelligence (AI) models that provide abilities of semantic extraction and recovery. Nevertheless, it is not feasible to preload all AI models on resource-constrained terminals. Thus, in-time model transmission becomes a crucial problem. This paper proposes an intellicise model transmission architecture to guarantee the reliable transmission of models for semantic communication. The mathematical relationship between model size and performance is formulated by employing a recognition error function supported with experimental data. We consider the characteristics of wireless channels and derive the closed-form expression of model transmission outage probability (MTOP) over the Rayleigh channel. Besides, we define the effective model accuracy (EMA) to evaluate the model transmission performance of both communication and intelligence. Then we propose a joint model selection and resource allocation (JMSRA) algorithm to maximize the average EMA of all users. Simulation results demonstrate that the average EMA of the JMSRA algorithm outperforms baseline algorithms by about 22%.