Align Entities With Ontologies: LLM-Enhanced Inductive Subgraph Reasoning Over Ontology-Based Knowledge Graphs.
TL;DR
A subgraph-aware semantic expansion module that coordinates $k$-hop neighborhood information with LLM-generated descriptions to alleviate structural sparsity and a contrastive ontology matching mechanism resolves structural inconsistencies by computing adaptive similarity metrics between ontology embeddings and subgraph-derived semantic prototypes.
Abstract
Ontology-based Knowledge Graphs (KGs) augment entity representation through additional semantic information, facilitating link prediction for unseen entities through predefined ontology libraries. While most existing knowledge graph representation learning methods predominantly focus on co-optimizing both entities and ontologies to leverage ontological contexts, the structural-semantic discrepancies in ontology-based KGs have been largely overlooked. Through graph structure analysis, we identify two fundamental limitations: (1) structural incompatibility between entity subgraph semantics and multi-ontology mappings (1-N redundancy), and (2) missing explicit ontology link in subgraph contexts (1-0 absence). To resolve these issues, we propose a structural empowered module built upon link prediction backbones. First, we develop a subgraph-aware semantic expansion module that coordinates $k$-hop neighborhood information with LLM-generated descriptions to alleviate structural sparsity. Subsequently, a contrastive ontology matching mechanism resolves structural inconsistencies by computing adaptive similarity metrics between ontology embeddings and subgraph-derived semantic prototypes. Experimental results demonstrate that our model outperforms fourteen state-of-the-art models, maintaining robust performance across varying benchmarks and subgraph density conditions.