A Survey of Link Prediction in N-ary Knowledge Graphs

2025-06-10

AI Summary

N-ary knowledge graphs (NKGs) model complex facts involving three or more entities, and their link prediction task requires completing any missing argument in an n-ary relation. This paper establishes the first systematic research framework for NKG link prediction, proposing a unified taxonomy grounded in representation learning, graph neural networks, and logical rules to characterize method capabilities and applicability conditions. Through rigorous cross-method evaluation of state-of-the-art models, we identify key performance differentiators and expose fundamental limitations of current benchmarks—namely insufficient scale, lack of dynamicity, and poor interpretability. Our core contributions are threefold: (i) the first comprehensive methodology framework for NKG link prediction; (ii) the identification of scalability, interpretability, and dynamic updating as the three principal future research directions; and (iii) theoretical foundations and practical guidelines for advancing NKG modeling and real-world deployment.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

N-ary Knowledge Graphs (NKGs) are a specialized type of knowledge graph designed to efficiently represent complex real-world facts. Unlike traditional knowledge graphs, where a fact typically involves two entities, NKGs can capture n-ary facts containing more than two entities. Link prediction in NKGs aims to predict missing elements within these n-ary facts, which is essential for completing NKGs and improving the performance of downstream applications. This task has recently gained significant attention. In this paper, we present the first comprehensive survey of link prediction in NKGs, providing an overview of the field, systematically categorizing existing methods, and analyzing their performance and application scenarios. We also outline promising directions for future research.

Problem

• Predict missing elements in n-ary knowledge graphs
• Survey link prediction methods for NKGs
• Analyze performance and applications of NKG methods

Innovation

• Survey of link prediction in NKGs
• Systematic categorization of existing methods
• Outline future research directions