Feature-Dependent Graph Convolutional Autoencoders with Adversarial Training Methods

Di Wu, MB

Feature-Dependent Graph Convolutional Autoencoders with Adversarial Training Methods

Di Wu, MB

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: The 2019 International Joint Conference on Neural Networks (IJCNN 2019), 2019, 2019-July, pp. 1-8
Issue Date:: 2019

Closed Access

	Filename	Description	Size
	08852314.pdf	Published version	752.03 kB	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	Di Wu, MB
dc.date	2019-07-14
dc.date.accessioned	2020-06-10T00:38:12Z
dc.date.available	2020-06-10T00:38:12Z
dc.date.issued	2019
dc.identifier.citation	The 2019 International Joint Conference on Neural Networks (IJCNN 2019), 2019, 2019-July, pp. 1-8
dc.identifier.isbn	9781728119854
dc.identifier.issn	2161-4393
dc.identifier.uri	http://hdl.handle.net/10453/141217
dc.description.abstract	© 2019 IEEE. Graphs are ubiquitous for describing and modeling complicated data structures, and graph embedding is an effective solution to learn a mapping from a graph to a low-dimensional vector space while preserving relevant graph characteristics. Most existing graph embedding approaches either embed the topological information and node features separately or learn one regularized embedding with both sources of information, however, they mostly overlook the interdependency between structural characteristics and node features when processing the graph data into the models. Moreover, existing methods only reconstruct the structural characteristics, which are unable to fully leverage the interaction between the topology and the features associated with its nodes during the encoding-decoding procedure. To address the problem, we propose a framework using autoencoder for graph embedding (GED) and its variational version (VEGD). The contribution of our work is two-fold: 1) the proposed frameworks exploit a feature-dependent graph matrix (FGM) to naturally merge the structural characteristics and node features according to their interdependency; and 2) the Graph Convolutional Network (GCN) decoder of the proposed framework reconstructs both structural characteristics and node features, which naturally possesses the interaction between these two sources of information while learning the embedding. We conducted the experiments on three real-world graph datasets such as Cora, Citeseer and PubMed to evaluate our framework and algorithms, and the results outperform baseline methods on both link prediction and graph clustering tasks.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	The 2019 International Joint Conference on Neural Networks (IJCNN 2019)
dc.relation.ispartof	2019 International Joint Conference on Neural Networks (IJCNN)
dc.relation.isbasedon	10.1109/IJCNN.2019.8852314
dc.rights	info:eu-repo/semantics/closedAccess
dc.rights	© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.title	Feature-Dependent Graph Convolutional Autoencoders with Adversarial Training Methods
dc.type	Conference Proceeding
utslib.citation.volume	2019-July
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Strength - QSI - Centre for Quantum Software and Information
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2020-06-10T00:38:08Z
pubs.finish-date	2019-07-19
pubs.publication-status	Published
pubs.start-date	2019-07-14
pubs.volume	2019-July

Abstract:

© 2019 IEEE. Graphs are ubiquitous for describing and modeling complicated data structures, and graph embedding is an effective solution to learn a mapping from a graph to a low-dimensional vector space while preserving relevant graph characteristics. Most existing graph embedding approaches either embed the topological information and node features separately or learn one regularized embedding with both sources of information, however, they mostly overlook the interdependency between structural characteristics and node features when processing the graph data into the models. Moreover, existing methods only reconstruct the structural characteristics, which are unable to fully leverage the interaction between the topology and the features associated with its nodes during the encoding-decoding procedure. To address the problem, we propose a framework using autoencoder for graph embedding (GED) and its variational version (VEGD). The contribution of our work is two-fold: 1) the proposed frameworks exploit a feature-dependent graph matrix (FGM) to naturally merge the structural characteristics and node features according to their interdependency; and 2) the Graph Convolutional Network (GCN) decoder of the proposed framework reconstructs both structural characteristics and node features, which naturally possesses the interaction between these two sources of information while learning the embedding. We conducted the experiments on three real-world graph datasets such as Cora, Citeseer and PubMed to evaluate our framework and algorithms, and the results outperform baseline methods on both link prediction and graph clustering tasks.

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

http://hdl.handle.net/10453/141217