UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15421-15429
DOI: 10.1609/aaai.v40i18.38569 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhiqiang Liu und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Real-world knowledge graphs (KGs) contain not only standard triple-based facts, but also more complex, heterogeneous types of facts, such as hyper-relational facts with auxiliary key-value pairs, temporal facts with additional timestamps, and nested facts that imply relationships between facts. These richer forms of representation have attracted significant attention due to their enhanced expressiveness and capacity to model complex semantics in real-world scenarios. However, most existing studies suffer from two main limitations: (1) they typically focus on modeling only specific types of facts, thus making it difficult to generalize to real-world scenarios with multiple fact types; and (2) they struggle to achieve generalizable hierarchical (inter-fact and intra-fact) modeling due to the complexity of these representations. To overcome these limitations, we propose UniHR, a Unified Hierarchical Representation learning framework, which consists of a learning-optimized Hierarchical Data Representation (HiDR) module and a unified Hierarchical Structure Learning (HiSL) module. 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 both semantic information within individual facts and enriching the structural information between facts. To go beyond the unified method itself, we further explore the potential of unified representation in complex real-world scenarios. Extensive experiments on 9 datasets across 5 types of KGs demonstrate the effectiveness of UniHR and highlight the strong potential of unified representations.
Zitieren
APA
Liu, Z., Hua, Y., Chen, M., Zhang, Y., Chen, Z., Liang, L., & Zhang, W. (2026). UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15421-15429. https://doi.org/10.1609/aaai.v40i18.38569
Vancouver
Liu Z, Hua Y, Chen M, Zhang Y, Chen Z, Liang L, et al. UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15421-15429. doi:10.1609/aaai.v40i18.38569
BibTeX
@article{Liu2026,
author = {Liu, Zhiqiang and Hua, Yin and Chen, Mingyang and Zhang, Yichi and Chen, Zhuo and Liang, Lei and Zhang, Wen},
title = {UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {18},
pages = {15421--15429},
doi = {10.1609/aaai.v40i18.38569}
}
EUVIMED