Multi-channel graph neural network for entity alignment
Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channel...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2019
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7461 https://ink.library.smu.edu.sg/context/sis_research/article/8464/viewcontent/P19_1140.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-8464 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-84642022-11-22T07:11:25Z Multi-channel graph neural network for entity alignment CAO, Yixin LIU, Zhiyuan LI, Chengjiang LIU, Zhiyuan LI, Juanzi CHUA, Tat-Seng Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make better use of seed alignments. Extensive experiments on five publicly available datasets demonstrate our superior performance (5% Hits@1 up on average). Source code and data used in the experiments can be accessed at https://github.com/thunlp/MuGNN. 2019-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7461 info:doi/10.18653/v1/P19-1140 https://ink.library.smu.edu.sg/context/sis_research/article/8464/viewcontent/P19_1140.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 Databases and Information Systems Graphics and Human Computer Interfaces OS and Networks |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Databases and Information Systems Graphics and Human Computer Interfaces OS and Networks |
spellingShingle |
Databases and Information Systems Graphics and Human Computer Interfaces OS and Networks CAO, Yixin LIU, Zhiyuan LI, Chengjiang LIU, Zhiyuan LI, Juanzi CHUA, Tat-Seng Multi-channel graph neural network for entity alignment |
description |
Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make better use of seed alignments. Extensive experiments on five publicly available datasets demonstrate our superior performance (5% Hits@1 up on average). Source code and data used in the experiments can be accessed at https://github.com/thunlp/MuGNN. |
format |
text |
author |
CAO, Yixin LIU, Zhiyuan LI, Chengjiang LIU, Zhiyuan LI, Juanzi CHUA, Tat-Seng |
author_facet |
CAO, Yixin LIU, Zhiyuan LI, Chengjiang LIU, Zhiyuan LI, Juanzi CHUA, Tat-Seng |
author_sort |
CAO, Yixin |
title |
Multi-channel graph neural network for entity alignment |
title_short |
Multi-channel graph neural network for entity alignment |
title_full |
Multi-channel graph neural network for entity alignment |
title_fullStr |
Multi-channel graph neural network for entity alignment |
title_full_unstemmed |
Multi-channel graph neural network for entity alignment |
title_sort |
multi-channel graph neural network for entity alignment |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2019 |
url |
https://ink.library.smu.edu.sg/sis_research/7461 https://ink.library.smu.edu.sg/context/sis_research/article/8464/viewcontent/P19_1140.pdf |
_version_ |
1770576342683746304 |