Knowledge Graph Completion: A Review
Дополнение графов знаний: обзор
2020-01-01
SCID: 54.1/uqfk3p9w
Discuss with AI
knowledge graph completionknowledge graph constructionmissing entity predictionrepresentation learningrule-based reasoning
Figures from the paper
Abstract (AI)
Knowledge graph completion (KGC) is a hot topic in knowledge graph construction and related applications, which aims to complete the structure of knowledge graph by predicting the missing entities or relationships in knowledge graph and mining unknown facts. Starting from the definition and types of KGC, existing technologies for KGC are analyzed in categories. From the evolving point of view, the KGC technologies could be divided into traditional and representation learning based methods. The former mainly includes rule-based reasoning method, probability graph model, such as Markov logic network, and graph computation based method. The latter further includes translation model based, semantic matching model based, representation learning based and other neural network model based methods. In this article, different KGC technologies are introduced, including their advantages, disadvantages and applicable fields. Finally the main challenges and problems faced by the KGC are discussed, as well as the potential research directions.
Key Findings
1
KGC technologies are categorized evolutionarily into traditional methods and representation-learning-based methods.
2
Knowledge graph completion predicts missing entities or relationships to complete graph structure and discover unknown facts.
3
Representation-learning approaches include translation models, semantic-matching models, other representation-learning techniques, and neural-network-based methods.
4
The review compares methods’ advantages, disadvantages, application fields, challenges, and potential future research directions.
5
Traditional approaches include rule-based reasoning, probabilistic graphical models such as Markov logic networks, and graph-computation methods.
Research Object
Knowledge graph completion (KGC) task/system
Research Subject
methods, advantages, disadvantages, applicability, challenges, and future directions for predicting missing entities or relationships and mining unknown facts
Publication Details
Publication Date
2020-01-01
Journal
Publisher
ISSN
Cited by
351
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai15
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Neural Machine Translation by Jointly Learning to Align and Translate2014
Convolutional Neural Networks for Sentence Classification2014
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: A Survey of Approaches and Applications2017
Convolutional 2D Knowledge Graph Embeddings2018
Knowledge Graphs2021
Knowledge Graph Embedding via Dynamic Mapping Matrix2015
A Review of Relational Machine Learning for Knowledge Graphs2015
Holographic Embeddings of Knowledge Graphs2016
TransG : A Generative Model for Knowledge Graph Embedding2016
Review on Knowledge Graph Techniques2016
Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks2024