Knowledge graph reasoning: modern methods and applications

Knowledge reasoning over knowledge graph aims to discover new knowledge according to the existing knowledge.It is a pivotal technology to realize the human reasoning and decision-making ability of machine.The modern methods of knowledge reasoning over knowledge graph were studied systematically.And...

Full description

Saved in:
Bibliographic Details
Main Author: Wenguang WANG
Format: Article
Language:zho
Published: China InfoCom Media Group 2021-05-01
Series:大数据
Subjects:
Online Access:http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2021025
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212469210873856
author Wenguang WANG
author_facet Wenguang WANG
author_sort Wenguang WANG
collection DOAJ
description Knowledge reasoning over knowledge graph aims to discover new knowledge according to the existing knowledge.It is a pivotal technology to realize the human reasoning and decision-making ability of machine.The modern methods of knowledge reasoning over knowledge graph were studied systematically.And the methods based on vector representations with a unified framework were introduced, including the methods based on embedding into Euclidean space and hyperbolic space, and based on deep learning methods such as convolution neural network, capsule network, graph neural network, etc.Simultaneously, the applications of knowledge reasoning in various technical fields and industries were presented, and the existing challenges and opportunities were pointed out as well.
format Article
id doaj-art-6f3fc5e68f114a8d9ba4451853c65c41
institution OA Journals
issn 2096-0271
language zho
publishDate 2021-05-01
publisher China InfoCom Media Group
record_format Article
series 大数据
spelling doaj-art-6f3fc5e68f114a8d9ba4451853c65c412025-08-20T02:09:21ZzhoChina InfoCom Media Group大数据2096-02712021-05-017202102559537831Knowledge graph reasoning: modern methods and applicationsWenguang WANGKnowledge reasoning over knowledge graph aims to discover new knowledge according to the existing knowledge.It is a pivotal technology to realize the human reasoning and decision-making ability of machine.The modern methods of knowledge reasoning over knowledge graph were studied systematically.And the methods based on vector representations with a unified framework were introduced, including the methods based on embedding into Euclidean space and hyperbolic space, and based on deep learning methods such as convolution neural network, capsule network, graph neural network, etc.Simultaneously, the applications of knowledge reasoning in various technical fields and industries were presented, and the existing challenges and opportunities were pointed out as well.http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2021025knowledge reasoning;hyperbolic space embedding;geometric operation;capsule network;graph neural network
spellingShingle Wenguang WANG
Knowledge graph reasoning: modern methods and applications
大数据
knowledge reasoning;hyperbolic space embedding;geometric operation;capsule network;graph neural network
title Knowledge graph reasoning: modern methods and applications
title_full Knowledge graph reasoning: modern methods and applications
title_fullStr Knowledge graph reasoning: modern methods and applications
title_full_unstemmed Knowledge graph reasoning: modern methods and applications
title_short Knowledge graph reasoning: modern methods and applications
title_sort knowledge graph reasoning modern methods and applications
topic knowledge reasoning;hyperbolic space embedding;geometric operation;capsule network;graph neural network
url http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2021025
work_keys_str_mv AT wenguangwang knowledgegraphreasoningmodernmethodsandapplications