A semantic communication-based workload-adjustable transceiver for wireless AI-generated content (AIGC) delivery

2025-03-24

AI Summary

To address semantic distortion and high end-to-end latency in dynamic wireless networks—caused by time-varying channels, bandwidth constraints, and heterogeneous computational resources—this paper proposes, for the first time, a co-design framework integrating semantic communication with adjustable-load diffusion models. The method jointly optimizes semantic representation learning, transmission scheduling, and edge–end collaborative generative inference to enable adaptive co-regulation of semantic density and computational load. It integrates a lightweight diffusion model, resource-aware joint optimization, and semantic-priority transmission, ensuring high-fidelity reconstruction even under low SNR and narrowband conditions. Experimental results demonstrate a 37% reduction in end-to-end latency and a 29% improvement in semantic fidelity, significantly outperforming conventional digital communication and standalone model deployment approaches.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

With the significant advances in generative AI (GAI) and the proliferation of mobile devices, providing high-quality AI-generated content (AIGC) services via wireless networks is becoming the future direction. However, the primary challenges of AIGC service delivery in wireless networks lie in unstable channels, limited bandwidth resources, and unevenly distributed computational resources. In this paper, we employ semantic communication (SemCom) in diffusion-based GAI models to propose a Resource-aware wOrkload-adjUstable TransceivEr (ROUTE) for AIGC delivery in dynamic wireless networks. Specifically, to relieve the communication resource bottleneck, SemCom is utilized to prioritize semantic information of the generated content. Then, to improve computational resource utilization in both edge and local and reduce AIGC semantic distortion in transmission, modified diffusion-based models are applied to adjust the computing workload and semantic density in cooperative content generation. Simulations verify the superiority of our proposed ROUTE in terms of latency and content quality compared to conventional AIGC approaches.

Problem

• Unstable channels and limited bandwidth in wireless AIGC delivery
• Uneven computational resource distribution for AIGC services
• Semantic distortion and high latency in content transmission

Innovation

• Semantic communication for content prioritization
• Modified diffusion models for workload adjustment
• Resource-aware transceiver for dynamic networks