Generative Semantic Communications: Principles and Practices

2025-04-21

AI Summary

To address the high overhead and low fidelity challenges in semantic communication arising from the rapid proliferation of AGI services, this paper proposes Generative Semantic Communication (GSC), a novel paradigm. GSC introduces the first systematic, end-to-end semantic communication framework driven by Artificial General Intelligence, integrating large language models, diffusion models, and semantic encoders to jointly extract, generate, and context-adaptively reconstruct semantic representations—thereby overcoming the limitation of conventional semantic communication frameworks that rely on predefined semantic units. Through task-oriented joint optimization, GSC achieves over 70% reduction in transmission overhead across two representative AGI applications, while maintaining task performance nearly equivalent to that of raw-data communication. This demonstrates substantial improvements in intelligence, generalizability, and efficiency of semantic communication systems.

Technology Category

• Multiagent Systems: Agent Communication
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Semantic communication leverages artificial intelligence (AI) technologies to extract semantic information from data for efficient transmission, theraby significantly reducing communication cost. With the evolution towards artificial general intelligence (AGI), the increasing demands for AGI services pose new challenges to semantic communication. In response, we propose a new paradigm for AGI-driven communications, called generative semantic communication (GSC), which utilizes advanced AI technologies such as foundation models and generative models. We first describe the basic concept of GSC and its difference from existing semantic communications, and then introduce a general framework of GSC, followed by two case studies to verify the advantages of GSC in AGI-driven applications. Finally, open challenges and new research directions are discussed to stimulate this line of research and pave the way for practical applications.

Problem

• Proposes generative semantic communication for AGI-driven services
• Addresses challenges in efficient semantic information transmission
• Introduces framework and case studies for GSC advantages

Innovation

• Utilizes foundation models for semantic extraction
• Employs generative models for efficient communication
• Proposes AGI-driven generative semantic communication framework