LargeEA: Aligning entities for large-scale knowledge graphs
Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). Current EA approaches suffer from scalability issues, limiting their usage in real-world EA scenarios. To tackle this challenge, we propose LargeEA to align entities between large-scale KGs. LargeEA consists...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7178 https://ink.library.smu.edu.sg/context/sis_research/article/8181/viewcontent/3489496.3489504.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8181 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-81812022-07-07T02:59:56Z LargeEA: Aligning entities for large-scale knowledge graphs GE, Congcong LIU, Xiaoze CHEN, Lu GAO, Yunjun ZHENG, Baihua Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). Current EA approaches suffer from scalability issues, limiting their usage in real-world EA scenarios. To tackle this challenge, we propose LargeEA to align entities between large-scale KGs. LargeEA consists of two channels, i.e., structure channel and name channel. For the structure channel, we present METIS-CPS, a memory-saving mini-batch generation strategy, to partition large KGs into smaller mini-batches. LargeEA, designed as a general tool, can adopt any existing EA approach to learn entities’ structural features within each mini-batch independently. For the name channel, we first introduce NFF, a name feature fusion method, to capture rich name features of entities without involving any complex training process; we then exploit a name-based data augmentation to generate seed alignment without any human intervention. Such design fits common real-world scenarios much better, as seed alignment is not always available. Finally, LargeEA derives the EA results by fusing the structural features and name features of entities. Since no widely-acknowledged benchmark is available for large-scale EA evaluation, we also develop a largescale EA benchmark called DBP1M extracted from real-world KGs. Extensive experiments confirm the superiority of LargeEA against state-of-the-art competitors. 2022-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7178 info:doi/10.14778/3489496.3489504 https://ink.library.smu.edu.sg/context/sis_research/article/8181/viewcontent/3489496.3489504.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Graphics and Human Computer Interfaces |
spellingShingle |
Graphics and Human Computer Interfaces GE, Congcong LIU, Xiaoze CHEN, Lu GAO, Yunjun ZHENG, Baihua LargeEA: Aligning entities for large-scale knowledge graphs |
description |
Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). Current EA approaches suffer from scalability issues, limiting their usage in real-world EA scenarios. To tackle this challenge, we propose LargeEA to align entities between large-scale KGs. LargeEA consists of two channels, i.e., structure channel and name channel. For the structure channel, we present METIS-CPS, a memory-saving mini-batch generation strategy, to partition large KGs into smaller mini-batches. LargeEA, designed as a general tool, can adopt any existing EA approach to learn entities’ structural features within each mini-batch independently. For the name channel, we first introduce NFF, a name feature fusion method, to capture rich name features of entities without involving any complex training process; we then exploit a name-based data augmentation to generate seed alignment without any human intervention. Such design fits common real-world scenarios much better, as seed alignment is not always available. Finally, LargeEA derives the EA results by fusing the structural features and name features of entities. Since no widely-acknowledged benchmark is available for large-scale EA evaluation, we also develop a largescale EA benchmark called DBP1M extracted from real-world KGs. Extensive experiments confirm the superiority of LargeEA against state-of-the-art competitors. |
format |
text |
author |
GE, Congcong LIU, Xiaoze CHEN, Lu GAO, Yunjun ZHENG, Baihua |
author_facet |
GE, Congcong LIU, Xiaoze CHEN, Lu GAO, Yunjun ZHENG, Baihua |
author_sort |
GE, Congcong |
title |
LargeEA: Aligning entities for large-scale knowledge graphs |
title_short |
LargeEA: Aligning entities for large-scale knowledge graphs |
title_full |
LargeEA: Aligning entities for large-scale knowledge graphs |
title_fullStr |
LargeEA: Aligning entities for large-scale knowledge graphs |
title_full_unstemmed |
LargeEA: Aligning entities for large-scale knowledge graphs |
title_sort |
largeea: aligning entities for large-scale knowledge graphs |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2022 |
url |
https://ink.library.smu.edu.sg/sis_research/7178 https://ink.library.smu.edu.sg/context/sis_research/article/8181/viewcontent/3489496.3489504.pdf |
_version_ |
1770576252806103040 |