EUVIMEDEUVIMED entdecken
Crossref

NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning

Bo Xiong, Mojtaba Nayyeri, Linhao Luo, Zihao Wang, Shirui Pan, Steffen Staab

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (8) · 9205-9213

DOI: 10.1609/aaai.v38i8.28772 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Bo Xiong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reasoning with knowledge graphs (KGs) has primarily focused on triple-shaped facts. Recent advancements have been explored to enhance the semantics of these facts by incorporating more potent representations, such as hyper-relational facts. However, these approaches are limited to atomic facts, which describe a single piece of information. This paper extends beyond atomic facts and delves into nested facts, represented by quoted triples where subjects and objects are triples themselves (e.g., ((BarackObama, holds_position, President), succeed_by, (DonaldTrump, holds_position, President))). These nested facts enable the expression of complex semantics like situations over time and logical patterns} over entities and relations. In response, we introduce NestE, a novel KG embedding approach that captures the semantics of both atomic and nested factual knowledge. NestE represents each atomic fact as a 1*3 matrix, and each nested relation is modeled as a 3*3 matrix that rotates the 1*3 atomic fact matrix through matrix multiplication. Each element of the matrix is represented as a complex number in the generalized 4D hypercomplex space, including (spherical) quaternions, hyperbolic quaternions, and split-quaternions. Through thorough analysis, we demonstrate the embedding's efficacy in capturing diverse logical patterns over nested facts, surpassing the confines of first-order logic-like expressions. Our experimental results showcase NestE's significant performance gains over current baselines in triple prediction and conditional link prediction. The code and pre-trained models are open available at https://github.com/xiongbo010/NestE.

Zitieren

APA

Xiong, B., Nayyeri, M., Luo, L., Wang, Z., Pan, S., & Staab, S. (2024). NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 9205-9213. https://doi.org/10.1609/aaai.v38i8.28772

Vancouver

Xiong B, Nayyeri M, Luo L, Wang Z, Pan S, Staab S. NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(8):9205-9213. doi:10.1609/aaai.v38i8.28772

BibTeX
@article{Xiong2024,
  author = {Xiong, Bo and Nayyeri, Mojtaba and Luo, Linhao and Wang, Zihao and Pan, Shirui and Staab, Steffen},
  title = {NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {8},
  pages = {9205--9213},
  doi = {10.1609/aaai.v38i8.28772}
}
Kostenlos starten →