A Survey of Link Prediction in N-ary Knowledge Graphs
Preprint
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.Keywords
All Related Versions
This publication has 54 references indexed in Scilit:
- MHRE: Multivariate link prediction method for medical hyper-relational factsApplied Intelligence, 2024
- What Is a Multi-Modal Knowledge Graph: A SurveyBig Data Research, 2023
- N-ary relation prediction based on knowledge graphs with important entity detectionExpert Systems with Applications, 2023
- A comprehensive overview of knowledge graph completionKnowledge-Based Systems, 2022
- A Comprehensive Survey of Graph Neural Networks for Knowledge GraphsIEEE Access, 2022
- Modeling N-ary relational data as gyro-polygons with learnable gyro-centroidKnowledge-Based Systems, 2022
- HYPER2: Hyperbolic embedding for hyper-relational link predictionNeurocomputing, 2022
- Improving Inductive Link Prediction Using Hyper-relational Facts2021
- Knowledge Graph Completion: A ReviewIEEE Access, 2020
- Research on Information Extraction of Technical Documents and Construction of Domain Knowledge GraphIEEE Access, 2020