arrow
返回

A multiscale convolutional gragh network using only structural information for entity alignment

delete2022-07-25
delete13
PRE
AI
D
Donglin Qi
陈曙东 封面图
陈曙东 (Shudong Chen)
X
Xiao Sun *
R
Ruipeng Luan
D
Da Tong
DOI:10.1007/s10489-022-03916-3delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
As an essential method of knowledge graph fusion, entity alignment aims to find entities that refer to the same real-world object in different knowledge graphs. Current entity alignment methods usually adopt extra information such as entity names, attribute triples except for structural information of the knowledge graph. However, due to the difficult availability and possibly low effectiveness of extra information, it is necessary to improve the performance of entity alignment when using only structural information. In this paper, a novel entity alignment method based on the multiscale convolutional graph network (MCEA) is proposed, which utilizes only structural information of the graph for entity alignment. Firstly, the convolution region of long-tail entities is extended to enhance the ability of information capture of the graph network. Secondly, intermediate results from semi-supervised learning are introduced to negative sampling in order to improve sampling quality. Thirdly, the stable marriage algorithm is chosen as the alignment strategy to obtain final alignment results. The experimental results show that this method has achieved better performance on Hits@K and MRR than the state-of-the-art methods, especially in the case of less labeled data. Moreover, we also find that the impact of the alignment strategy has become limited when the model generates sufficient accurate entity embeddings.
Keyword:
Entity alignment
Knowledge graph
Graph neural network
Semi-supervised learning

期刊

Applied Intelligence 封面图
Applied Intelligence
IF:
3.5
论文数:
7.6K
被引数:
1.7W

机构

U
university of chinese academy of sciences, cas
学者数:
4.1W
论文数: 3.8W
被引数: 75
C
chinese academy of sciences
学者数:
56.7W
论文数: 45.0W
被引数: 704
引用论文

引用论文

New Molecular Strategies for Early Lung Cancer Detection
err2009-06-11
err0
errOAAI
errLuis M. Montuenga; James L. Mulshine
err分享
err收藏
Present Status of Theory: 1/N Approach
err1984-01-01
err0
PREAI
errPhilip W. Anderson
err分享
err收藏
Study of the mechanical and microstructural state of platinum thin films
err1996-01-01
err0
PREAI
errV. Branger; V. Pelosin; K.F. Badawi; Ph. Goudeau
err分享
err收藏
c-myc gene amplification in selected node-negative breast cancer patients correlates with high rate of early relapse
err1992-01-01
err0
PREAI
errM Roux-Dosseto; S Romain; N Dussault; C Desideri; L Piana; P Bonnier; N Tubiana; P.M Martin
err分享
err收藏
Cryptanalysis of Round-Reduced Fantomas, Robin and iSCREAM
err2019-01-10
err0
errOAAI
errAshutosh Dhar Dwivedi; Shalini Dhar; Gautam Srivastava; Rajani Singh
err分享
err收藏
Epigallocatechin-3-gallate Increases Maximal Oxygen Uptake in Adult Humans
err2010-04-01
err0
errOAAI
errJENNIFER C. RICHARDS; MARK C. LONAC; TYLER K. JOHNSON; MELANI M. SCHWEDER; CHRISTOPHER BELL
err分享
err收藏
学者 查看更多内容