GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion

TL;DR

GS-Quant introduces a hierarchical, semantically coherent quantization framework for knowledge graph completion, enabling LLMs to better reason over graph structures by generating structured discrete codes.

Contribution

It proposes a novel hierarchical quantization method that encodes semantic and structural information into discrete codes for improved knowledge graph reasoning.

Findings

GS-Quant significantly outperforms existing baselines in KGC tasks.

The framework effectively captures hierarchical semantic and structural information.

Experimental results validate the benefits of structured codes for reasoning.

Abstract

Large Language Models (LLMs) have shown immense potential in Knowledge Graph Completion (KGC), yet bridging the modality gap between continuous graph embeddings and discrete LLM tokens remains a critical challenge. While recent quantization-based approaches attempt to align these modalities, they typically treat quantization as flat numerical compression, resulting in semantically entangled codes that fail to mirror the hierarchical nature of human reasoning. In this paper, we propose GS-Quant, a novel framework that generates semantically coherent and structurally stratified discrete codes for KG entities. Unlike prior methods, GS-Quant is grounded in the insight that entity representations should follow a linguistic coarse-to-fine logic. We introduce a Granular Semantic Enhancement module that injects hierarchical knowledge into the codebook, ensuring that earlier codes capture global semantic categories while later codes refine specific attributes. Furthermore, a Generative Structural Reconstruction module imposes causal dependencies on the code sequence, transforming independent discrete units into structured semantic descriptors. By expanding the LLM vocabulary with these learned codes, we enable the model to reason over graph structures isomorphically to natural language generation. Experimental results demonstrate that GS-Quant significantly outperforms existing text-based and embedding-based baselines. Our code is publicly available at https://github.com/mikumifa/GS-Quant.