Implicit Semantic Communication Based on Bayesian Reconstruction Framework

2025-11-13

IEEE Wireless Communications Letters

AI Summary

Traditional semantic communication relies on pairwise relational graphs, limiting its ability to model and transmit higher-order semantic interactions. To address this, we propose an implicit semantic communication framework grounded in Bayesian reconstruction—marking the first integration of hypergraph reasoning with Bayesian inference. At the transmitter, only pairwise relations are explicitly encoded; at the receiver, a Bayesian hypergraph neural network implicitly reconstructs higher-order hyperedges via probabilistic inference. This approach overcomes inherent limitations of graph-structured representations and establishes an end-to-end differentiable semantic encoding-decoding architecture. Evaluated on real-world datasets, our method achieves up to 90% hyperedge recovery accuracy, substantially improving reconstruction fidelity and generalization for complex semantic structures. It introduces a novel paradigm for efficient transmission of higher-order semantics.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

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: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Semantic communication is a novel communication paradigm that focuses on the transportation and delivery of the emph{meaning} of messages. Recent results have verified that a graphical structure provides the most expressive and structurally faithful formalism for representing the relational semantics in most information sources. However, most existing works represent the semantics based on pairwise relation-based graphs, which cannot capture the higher-order interactions that are essential for some semantic sources. This paper proposes a novel Bayesian hypergraph inference-based semantic communication framework that can directly recover implicit semantic information involving high-order hyperedges at the receiver based on the pairwise relation-based explicit semantics sent by the transmitter. Experimental results based on real-world datasets demonstrated that the proposed SBRF achieves up to 90% recovery accuracy of the high-order hyperedges based on the pairwise relation-based explicit semantics.

Problem

• Recovering implicit high-order semantic relationships from pairwise explicit semantics
• Addressing limitations of graph models in capturing complex semantic interactions
• Developing Bayesian framework for accurate reconstruction of hyperedge relationships

Innovation

• Bayesian hypergraph inference for semantic recovery
• Recovers implicit high-order semantic interactions
• Uses pairwise explicit semantics for hyperedge reconstruction