A Survey on Knowledge Graphs: Representation, Acquisition, and Applications
Обзор графов знаний: представление, получение и приложения
2021-04-26
SCID: 54.1/4f8k3xtu
Discuss with AI
knowledge graph completionknowledge graph embeddingknowledge graph representation learningknowledge graphstemporal knowledge graphs
Figures from the paper
Abstract (AI)
Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction toward cognition and human-level intelligence. In this survey, we provide a comprehensive review of the knowledge graph covering overall research topics about: 1) knowledge graph representation learning; 2) knowledge acquisition and completion; 3) temporal knowledge graph; and 4) knowledge-aware applications and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models, and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning are reviewed. We further explore several emerging topics, including metarelational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of data sets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.
Key Findings
1
It introduces unified taxonomies for knowledge graph representation learning based on representation space, scoring function, encoding model, and auxiliary information.
2
It provides curated datasets and open-source libraries for diverse knowledge graph tasks and identifies promising directions for future research.
3
Knowledge graph completion methods are organized into embedding approaches, path inference, and logical rule reasoning.
4
The survey highlights emerging directions including metarelational learning, commonsense reasoning, and temporal knowledge graphs.
5
The survey presents a comprehensive review of knowledge graph research spanning representation learning, knowledge acquisition and completion, temporal graphs, and knowledge-aware applications.
Research Object
Knowledge graphs
Research Subject
their representation, acquisition and completion, temporal modeling, and knowledge-aware applications
Publication Details
Publication Date
2021-04-26
Journal
Publisher
ISSN
Cited by
3250
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai20
The Protein Data Bank2000
Semi-Supervised Classification with Graph Convolutional Networks2016
WordNet: a lexical database for English1995
Neural Architectures for Named Entity Recognition2016
Knowledge Graph Embedding by Translating on Hyperplanes2014
Learning Entity and Relation Embeddings for Knowledge Graph Completion2015
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge2017
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
Knowledge graph refinement: A survey of approaches and evaluation methods2016
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning2017
K-BERT: Enabling Language Representation with Knowledge Graph2020
ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding2020
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction2020
Holographic Embeddings of Knowledge Graphs2016
A Frustratingly Easy Approach for Entity and Relation Extraction2021
TransG : A Generative Model for Knowledge Graph Embedding2016
Cited by12
Unifying Large Language Models and Knowledge Graphs: A Roadmap2024
Knowledge Graphs2021
Text Data Augmentation for Deep Learning2021
Artificial intelligence: A powerful paradigm for scientific research2021
A Survey on Knowledge Graph-Based Recommender Systems2020
Knowledge Graphs: Opportunities and Challenges2023
Knowledge Graph-Guided Retrieval Augmented Generation2025
Generative AI-Driven Semantic Communication Networks: Architecture, Technologies, and Applications2024
Designing Data Spaces2022
Defining a Knowledge Graph Development Process Through a Systematic Review2022
Construction of Knowledge Graphs: Current State and Challenges2024
Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion2023