MGAE: Marginalized graph autoencoder for graph clustering

Wang, C; Pan, S; Long, G; Zhu, X; Jiang, J

MGAE: Marginalized graph autoencoder for graph clustering

Wang, C Pan, S

Long, G

Zhu, X Jiang, J

Permalink

Publication Type:: Conference Proceeding
Citation:: International Conference on Information and Knowledge Management, Proceedings, 2017, Part F131841 pp. 889 - 898
Issue Date:: 2017-11-06

Closed Access

	Filename	Description	Size
	p889-wang.pdf	Published version	2.07 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, C	en_US
dc.contributor.author	Pan, S https://orcid.org/0000-0003-0794-527X	en_US
dc.contributor.author	Long, G https://orcid.org/0000-0003-3740-9515	en_US
dc.contributor.author	Zhu, X	en_US
dc.contributor.author	Jiang, J https://orcid.org/0000-0001-5301-7779	en_US
dc.date.issued	2017-11-06	en_US
dc.identifier.citation	International Conference on Information and Knowledge Management, Proceedings, 2017, Part F131841 pp. 889 - 898	en_US
dc.identifier.isbn	9781450349185	en_US
dc.identifier.uri	http://hdl.handle.net/10453/127537
dc.description.abstract	© 2017 ACM. Graph clustering aims to discover community structures in networks, the task being fundamentally challenging mainly because the topology structure and the content of the graphs are dicult to represent for clustering analysis. Recently, graph clustering has moved from traditional shallow methods to deep learning approaches, thanks to the unique feature representation learning capability of deep learning. However, existing deep approaches for graph clustering can only exploit the structure information, while ignoring the content information associated with the nodes in a graph. In this paper, we propose a novel marginalized graph autoencoder (MGAE) algorithm for graph clustering. The key innovation of MGAE is that it advances the autoencoder to the graph domain, so graph representation learning can be carried out not only in a purely unsupervised se.ing by leveraging structure and content information, it can also be stacked in a deep fashion to learn effective representation. From a technical viewpoint, we propose a marginalized graph convolutional network to corrupt network node content, allowing node content to interact with network features, and marginalizes the corrupted features in a graph autoencoder context to learn graph feature representations. The learned features are fed into the spectral clustering algorithm for graph clustering. Experimental results on benchmark datasets demonstrate the superior performance of MGAE, compared to numerous baselines.	en_US
dc.relation.ispartof	International Conference on Information and Knowledge Management, Proceedings	en_US
dc.relation.isbasedon	10.1145/3132847.3132967	en_US
dc.title	MGAE: Marginalized graph autoencoder for graph clustering	en_US
dc.type	Conference Proceeding
utslib.citation.volume	Part F131841	en_US
utslib.for	0806 Information Systems	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAI - Advanced Analytics Institute Research Centre
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	Part F131841	en_US

Abstract:

© 2017 ACM. Graph clustering aims to discover community structures in networks, the task being fundamentally challenging mainly because the topology structure and the content of the graphs are dicult to represent for clustering analysis. Recently, graph clustering has moved from traditional shallow methods to deep learning approaches, thanks to the unique feature representation learning capability of deep learning. However, existing deep approaches for graph clustering can only exploit the structure information, while ignoring the content information associated with the nodes in a graph. In this paper, we propose a novel marginalized graph autoencoder (MGAE) algorithm for graph clustering. The key innovation of MGAE is that it advances the autoencoder to the graph domain, so graph representation learning can be carried out not only in a purely unsupervised se.ing by leveraging structure and content information, it can also be stacked in a deep fashion to learn effective representation. From a technical viewpoint, we propose a marginalized graph convolutional network to corrupt network node content, allowing node content to interact with network features, and marginalizes the corrupted features in a graph autoencoder context to learn graph feature representations. The learned features are fed into the spectral clustering algorithm for graph clustering. Experimental results on benchmark datasets demonstrate the superior performance of MGAE, compared to numerous baselines.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/127537