Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods

2025-06-05

AI Summary

Real-world knowledge often involves high-order n-ary relations, yet conventional knowledge graphs (KGs) flatten them into binary triples—causing semantic loss—while hypergraph models ignore role distinctions among entities within hyperedges. Method: We propose the first orthogonal two-dimensional taxonomy: the horizontal axis categorizes methodologies (e.g., translation-based, tensor decomposition, neural networks), and the vertical axis hierarchically classifies role-awareness granularity (role-agnostic, position-aware, role-aware), unifying modeling paradigms for knowledge hypergraphs and hyper-relational KGs. Our framework integrates KG principles, hypergraph theory, tensor decomposition, deep neural networks, logical rules, and hyperedge expansion techniques, covering the full pipeline—from data construction and negative sampling to evaluation. Contribution/Results: We systematically survey methodological evolution, benchmark datasets, and evaluation protocols; identify critical challenges—including insufficient role modeling and weak interpretability—and provide a structured research guide and paradigmatic framework for n-ary knowledge representation learning.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Knowledge Representation Languages
• Machine Learning: Graph-based Machine Learning

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Real-world knowledge can take various forms, including structured, semi-structured, and unstructured data. Among these, knowledge graphs are a form of structured human knowledge that integrate heterogeneous data sources into structured representations but typically reduce complex n-ary relations to simple triples, thereby losing higher-order relational details. In contrast, hypergraphs naturally represent n-ary relations with hyperedges, which directly connect multiple entities together. Yet hypergraph representation learning often overlooks entity roles in hyperedges, limiting the fine-grained semantic modelling. To address these issues, knowledge hypergraphs and hyper-relational knowledge graphs combine the advantages of knowledge graphs and hypergraphs to better capture the complex structures and role-specific semantics of real-world knowledge. This survey provides a comprehensive review of methods handling n-ary relational data, covering both knowledge hypergraphs and hyper-relational knowledge graphs literatures. We propose a two-dimensional taxonomy: the first dimension categorises models based on their methodology, i.e., translation-based models, tensor factorisation-based models, deep neural network-based models, logic rules-based models, and hyperedge expansion-based models. The second dimension classifies models according to their awareness of entity roles and positions in n-ary relations, dividing them into aware-less, position-aware, and role-aware approaches. Finally, we discuss existing datasets, negative sampling strategies, and outline open challenges to inspire future research.

Problem

• Addresses loss of higher-order relational details in knowledge graphs
• Improves semantic modeling by considering entity roles in hyperedges
• Proposes taxonomy for n-ary relation methods with role awareness

Innovation

• Combines knowledge graphs and hypergraphs advantages
• Proposes two-dimensional taxonomy for n-ary relations
• Categorizes models by methodology and role awareness