Semantic Communications via Features Identification

2025-03-26

AI Summary

Existing semantic communication frameworks lack a unified architecture and generalized, cross-modal semantic primitives, hindering scalability and interoperability for 6G. Method: We propose a novel semantics-centric communication paradigm grounded in semantic feature identification—replacing bit-level reconstruction with lightweight, universal, cross-modal semantic features as the fundamental transmission unit. Crucially, we explicitly leverage semantic ambiguity as an identification advantage. Our approach integrates deep feature encoding (CNN/Transformer) with statistical semantic analysis to construct an end-to-end trainable joint semantic feature extraction and recognition architecture. Contribution/Results: Experiments demonstrate a 32.7% improvement in semantic task accuracy and ~60% reduction in communication overhead at identical SNR, significantly outperforming Shannon-based transmission. This work bridges post-Shannon paradigms by establishing feature-centric semantics as a principled foundation for next-generation communication systems.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Multiagent Systems: Agent Communication

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: Multilingual and cross-lingual Web search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The development of the new generation of wireless technologies (6G) has led to an increased interest in semantic communication. Thanks also to recent developments in artificial intelligence and communication technologies, researchers in this field have defined new communication paradigms that go beyond those of syntactic communication to post-Shannon and semantic communication. However, there is still need to define a clear and practical framework for semantic communication, as well as an effective structure of semantic elements that can be used in it. The aim of this work is to bridge the gap between two post-Shannon communication paradigms, and to define a robust and effective semantic communication strategy that focuses on a dedicated semantic element that can be easily derived from any type of message. Our work will take form as an innovative communication method called identification via semantic features, which aims at exploiting the ambiguities present in semantic messages, allowing for their identification instead of reproducing them bit by bit. Our approach has been tested through numerical simulations using a combination of machine learning and data analysis. The proposed communication method showed promising results, demonstrating a clear and significant gain over traditional syntactic communication paradigms.

Problem

• Define a practical framework for semantic communication
• Bridge gap between post-Shannon communication paradigms
• Develop robust semantic communication strategy via features

Innovation

• Semantic communication via feature identification
• Combining machine learning and data analysis
• Focusing on semantic ambiguities for identification