Knowledge Graph-Based Explainable and Generalized Zero-Shot Semantic Communications

2025-07-02

AI Summary

To address the poor interpretability and weak generalization of data-driven semantic communication in zero-shot scenarios, this paper proposes a knowledge graph-enhanced zero-shot semantic communication framework. The framework constructs a structured semantic basis library and aligns category semantics with knowledge graph embeddings, enabling semantic compression at the transmitter and interpretable, retraining-free inference at the receiver. It is the first work to incorporate structured prior knowledge—encoded via knowledge graphs—into semantic communication systems, thereby supporting direct classification and semantic understanding of unseen categories. Experiments on the APY dataset demonstrate that the proposed method significantly outperforms existing semantic communication approaches across multiple signal-to-noise ratios, achieving superior robustness, high communication efficiency, and strong cross-category generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• 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
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Data-driven semantic communication is based on superficial statistical patterns, thereby lacking interpretability and generalization, especially for applications with the presence of unseen data. To address these challenges, we propose a novel knowledge graph-enhanced zero-shot semantic communication (KGZS-SC) network. Guided by the structured semantic information from a knowledge graph-based semantic knowledge base (KG-SKB), our scheme provides generalized semantic representations and enables reasoning for unseen cases. Specifically, the KG-SKB aligns the semantic features in a shared category semantics embedding space and enhances the generalization ability of the transmitter through aligned semantic features, thus reducing communication overhead by selectively transmitting compact visual semantics. At the receiver, zero-shot learning (ZSL) is leveraged to enable direct classification for unseen cases without the demand for retraining or additional computational overhead, thereby enhancing the adaptability and efficiency of the classification process in dynamic or resource-constrained environments. The simulation results conducted on the APY datasets show that the proposed KGZS-SC network exhibits robust generalization and significantly outperforms existing SC frameworks in classifying unseen categories across a range of SNR levels.

Problem

• Enhance interpretability and generalization in semantic communications
• Enable reasoning for unseen data using knowledge graphs
• Reduce communication overhead with selective semantic transmission

Innovation

• Knowledge graph-enhanced semantic communication network
• Aligned semantic features reduce communication overhead
• Zero-shot learning enables classification without retraining