UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction

ACL ARR 2025 February Submission589 Authors

Abstract: Beyond-triple fact representations including hyper-relational facts with auxiliary key-value pairs, temporal facts with additional timestamps, and nested facts implying relationships between facts, are gaining significant attention. However, existing link prediction models are usually designed for one specific type of facts, making it difficult to generalize to other types of facts. To overcome this limitation, we propose a Unified Hierarchical Representation learning framework (UniHR) for unified knowledge graph link prediction. It consists of a unified Hierarchical Data Representation (HiDR) module and a unified Hierarchical Structure Learning (HiSL) module as graph encoder. The HiDR module unifies hyper-relational KGs, temporal KGs, and nested factual KGs into triple-based representations. Then HiSL incorporates intra-fact and inter-fact message passing, focusing on enhancing the semantic information within individual facts and enriching the structural information between facts. Empirical results demonstrate the effectiveness of UniHR and highlight the strong potential of unified representations. Code and data are available at https://anonymous.4open.science/r/UniHR-BDCB/.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: knowledge graph

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 589