Knowledge Graph Embedding: A Survey of Approaches and Applications
Встраивание графа знаний: обзор подходов и приложений
2017-09-20
SCID: 54.1/g5arpjch
Discuss with AI
KG completionentity typesknowledge graph embeddingrelation extractiontextual descriptions
Figures from the paper
Abstract (AI)
Knowledge graph (KG) embedding is to embed components of a KG including entities and relations into continuous vector spaces, so as to simplify the manipulation while preserving the inherent structure of the KG. It can benefit a variety of downstream tasks such as KG completion and relation extraction, and hence has quickly gained massive attention. In this article, we provide a systematic review of existing techniques, including not only the state-of-the-arts but also those with latest trends. Particularly, we make the review based on the type of information used in the embedding task. Techniques that conduct embedding using only facts observed in the KG are first introduced. We describe the overall framework, specific model design, typical training procedures, as well as pros and cons of such techniques. After that, we discuss techniques that further incorporate additional information besides facts. We focus specifically on the use of entity types, relation paths, textual descriptions, and logical rules. Finally, we briefly introduce how KG embedding can be applied to and benefit a wide variety of downstream tasks such as KG completion, relation extraction, question answering, and so forth.
Key Findings
1
Incorporating additional information—entity types, relation paths, textual descriptions, and logical rules—enhances KG embedding techniques beyond fact-only methods.
2
KG embedding maps entities and relations into continuous vector spaces to preserve KG structure and simplify manipulation.
3
KG embeddings benefit multiple downstream tasks including KG completion, relation extraction, and question answering.
4
Models that use only observed KG facts are categorized, with descriptions of frameworks, model designs, training procedures, and their pros and cons.
Research Object
Knowledge graph embedding methods (algorithms that embed KG components—entities and relations—into continuous vector spaces)
Research Subject
Techniques and their design/training that preserve KG structure using different information types (observed facts, entity types, relation paths, textual descriptions, logical rules) and their applications to downstream tasks
Publication Details
Publication Date
2017-09-20
Journal
Publisher
ISSN
Cited by
2724
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai11
Distributed Representations of Words and Phrases and their Compositionality2013
A Stochastic Approximation Method1951
Improving neural networks by preventing co-adaptation of feature detectors2012
Knowledge Graph Embedding by Translating on Hyperplanes2014
Learning Entity and Relation Embeddings for Knowledge Graph Completion2015
DBpedia – A large-scale, multilingual knowledge base extracted from Wikipedia2015
Knowledge Graph Embedding via Dynamic Mapping Matrix2015
A Review of Relational Machine Learning for Knowledge Graphs2015
Knowledge graph refinement: A survey of approaches and evaluation methods2016
Holographic Embeddings of Knowledge Graphs2016
TransG : A Generative Model for Knowledge Graph Embedding2016
Cited by13
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications2021
Knowledge Graphs2021
Vision, challenges, roles and research issues of Artificial Intelligence in Education2020
A Survey on Knowledge Graph-Based Recommender Systems2020
Knowledge Graph Embedding for Link Prediction: A Comparative Analysis2021
Traffic Flow Prediction via Spatial Temporal Graph Neural Network2020
Knowledge Graph Completion: A Review2020
Constructing knowledge graphs and their biomedical applications2020
Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects2026
User Response Prediction in Online Advertising2021
Knowledge Graph Construction: Extraction, Learning, and Evaluation2025
Triple Classification for Scholarly Knowledge Graph Completion2021
Research hypothesis generation over scientific knowledge graphs2025