Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context
This work addresses scalability and contextual limitations in knowledge graph completion for applications like semantic search and AI reasoning, representing an incremental improvement over existing text-based methods.
The paper tackles the problem of incomplete knowledge graphs by proposing KGC-ERC, a framework that integrates entity neighborhood and relation context to enhance generative language models for knowledge graph completion, achieving state-of-the-art or competitive results on datasets like Wikidata5M, Wiki27K, and FB15K-237-N.
Knowledge Graph Completion (KGC) aims to infer missing information in Knowledge Graphs (KGs) to address their inherent incompleteness. Traditional structure-based KGC methods, while effective, face significant computational demands and scalability challenges due to the need for dense embedding learning and scoring all entities in the KG for each prediction. Recent text-based approaches using language models like T5 and BERT have mitigated these issues by converting KG triples into text for reasoning. However, they often fail to fully utilize contextual information, focusing mainly on the neighborhood of the entity and neglecting the context of the relation. To address this issue, we propose KGC-ERC, a framework that integrates both types of context to enrich the input of generative language models and enhance their reasoning capabilities. Additionally, we introduce a sampling strategy to effectively select relevant context within input token constraints, which optimizes the utilization of contextual information and potentially improves model performance. Experiments on the Wikidata5M, Wiki27K, and FB15K-237-N datasets show that KGC-ERC outperforms or matches state-of-the-art baselines in predictive performance and scalability.