Knowledge graph and knowledge reasoning: A systematic review
Граф знаний и рассуждения на графах знаний: систематический обзор
2022-05-31
SCID: 54.1/s6x4ana3
Discuss with AI
hyper-relational dataknowledge graph reasoningknowledge graphsknowledge hypergraphsneural network-based reasoning
Figures from the paper
Abstract (AI)
The knowledge graph (KG) that represents structural relations among entities has become an increasingly important research field for knowledge-driven artificial intelligence. In this survey, a comprehensive review of KG and KG reasoning is provided. It introduces an overview of KGs, including representation, storage, and essential technologies. Specifically, it summarizes several types of knowledge reasoning approaches, including logic rules-based, representation-based, and neural network-based methods. Moreover, this paper analyzes the representation methods of knowledge hypergraphs. To effectively model hyper-relational data and improve the performance of knowledge reasoning, a three-layer knowledge hypergraph model is proposed. Finally, it analyzes the advantages of three-layer knowledge hypergraphs through reasoning and update algorithms which could facilitate future research.
Key Findings
1
A three-layer knowledge hypergraph model is proposed to improve hyper-relational data modeling and knowledge reasoning performance.
2
It categorizes knowledge graph reasoning approaches into logic-rule-based, representation-based, and neural-network-based methods.
3
Reasoning and update algorithms demonstrate advantages of three-layer knowledge hypergraphs and support directions for future research.
4
The paper analyzes representation methods for knowledge hypergraphs to address modeling of hyper-relational data.
5
The survey comprehensively reviews knowledge graphs, covering their representation, storage, and essential supporting technologies.
Research Object
knowledge graphs and three-layer knowledge hypergraphs
Research Subject
their representation, storage, reasoning approaches, hyper-relational modeling, and reasoning/update performance
Publication Details
Publication Date
2022-05-31
Journal
Publisher
ISSN
Cited by
136
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
WordNet: a lexical database for English1995
Knowledge Graph Embedding by Translating on Hyperplanes2014
Learning Entity and Relation Embeddings for Knowledge Graph Completion2015
Knowledge Graph Embedding via Dynamic Mapping Matrix2015
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning2017
TransG : A Generative Model for Knowledge Graph Embedding2016