Heterogeneous graph neural network with multi-view representation learning
In recent years, graph neural networks (GNNs)-based methods have been widely adopted for heterogeneous graph (HG) embedding, due to their power in effectively encoding rich information from a HG into the low-dimensional node embeddings. However, previous works usually easily fail to fully leverage t...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8607 https://ink.library.smu.edu.sg/context/sis_research/article/9610/viewcontent/Heterogeneous_Graph_Neural_Network_With_Multi_View_Representation_Learning.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-9610 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-96102024-01-25T08:28:05Z Heterogeneous graph neural network with multi-view representation learning SHAO, Zezhi XU, Yongjun WEI, Wei WANG, Fei ZHANG, Zhao ZHU, Feida In recent years, graph neural networks (GNNs)-based methods have been widely adopted for heterogeneous graph (HG) embedding, due to their power in effectively encoding rich information from a HG into the low-dimensional node embeddings. However, previous works usually easily fail to fully leverage the inherent heterogeneity and rich semantics contained in the complex local structures of HGs. On the one hand, most of the existing methods either inadequately model the local structure under specific semantics, or neglect the heterogeneity when aggregating information from the local structure. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain node embeddings with versatility. To address the problem, we propose a Heterogeneous Graph Neural Network for HG embedding within a Multi-View representation learning framework (named MV-HetGNN), which consists of a view-specific ego graph encoder and auto multi-view fusion layer. MV-HetGNN thoroughly learns complex heterogeneity and semantics in the local structure to generate comprehensive and versatile node representations for HGs. Extensive experiments on three real-world HG datasets demonstrate the significant superiority of our proposed MV-HetGNN compared to the state-of-the-art baselines in various downstream tasks, e.g., node classification, node clustering, and link prediction. 2023-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8607 info:doi/10.1109/TKDE.2022.3224193 https://ink.library.smu.edu.sg/context/sis_research/article/9610/viewcontent/Heterogeneous_Graph_Neural_Network_With_Multi_View_Representation_Learning.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 Heterogeneous graphs Graph neural networks Graph embedding Databases and Information Systems Numerical Analysis and Scientific Computing |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Heterogeneous graphs Graph neural networks Graph embedding Databases and Information Systems Numerical Analysis and Scientific Computing |
spellingShingle |
Heterogeneous graphs Graph neural networks Graph embedding Databases and Information Systems Numerical Analysis and Scientific Computing SHAO, Zezhi XU, Yongjun WEI, Wei WANG, Fei ZHANG, Zhao ZHU, Feida Heterogeneous graph neural network with multi-view representation learning |
description |
In recent years, graph neural networks (GNNs)-based methods have been widely adopted for heterogeneous graph (HG) embedding, due to their power in effectively encoding rich information from a HG into the low-dimensional node embeddings. However, previous works usually easily fail to fully leverage the inherent heterogeneity and rich semantics contained in the complex local structures of HGs. On the one hand, most of the existing methods either inadequately model the local structure under specific semantics, or neglect the heterogeneity when aggregating information from the local structure. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain node embeddings with versatility. To address the problem, we propose a Heterogeneous Graph Neural Network for HG embedding within a Multi-View representation learning framework (named MV-HetGNN), which consists of a view-specific ego graph encoder and auto multi-view fusion layer. MV-HetGNN thoroughly learns complex heterogeneity and semantics in the local structure to generate comprehensive and versatile node representations for HGs. Extensive experiments on three real-world HG datasets demonstrate the significant superiority of our proposed MV-HetGNN compared to the state-of-the-art baselines in various downstream tasks, e.g., node classification, node clustering, and link prediction. |
format |
text |
author |
SHAO, Zezhi XU, Yongjun WEI, Wei WANG, Fei ZHANG, Zhao ZHU, Feida |
author_facet |
SHAO, Zezhi XU, Yongjun WEI, Wei WANG, Fei ZHANG, Zhao ZHU, Feida |
author_sort |
SHAO, Zezhi |
title |
Heterogeneous graph neural network with multi-view representation learning |
title_short |
Heterogeneous graph neural network with multi-view representation learning |
title_full |
Heterogeneous graph neural network with multi-view representation learning |
title_fullStr |
Heterogeneous graph neural network with multi-view representation learning |
title_full_unstemmed |
Heterogeneous graph neural network with multi-view representation learning |
title_sort |
heterogeneous graph neural network with multi-view representation learning |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/8607 https://ink.library.smu.edu.sg/context/sis_research/article/9610/viewcontent/Heterogeneous_Graph_Neural_Network_With_Multi_View_Representation_Learning.pdf |
_version_ |
1789483285791899648 |