Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning

Wan, S; Pan, S; Yang, J; Gong, C

Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning

Wan, S Pan, S

Yang, J Gong, C

Permalink

Publisher:: AAAI
Publication Type:: Conference Proceeding
Citation:: THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35, pp. 10049-10057
Issue Date:: 2021-01-01

Closed Access

	Filename	Description	Size
	17206-Article Text-20700-1-2-20210518 (2).pdf	Published version	467.7 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	Wan, S
dc.contributor.author	Pan, S https://orcid.org/0000-0003-0794-527X
dc.contributor.author	Yang, J
dc.contributor.author	Gong, C
dc.date	2021-02-02
dc.date.accessioned	2022-06-26T04:02:18Z
dc.date.available	2022-06-26T04:02:18Z
dc.date.issued	2021-01-01
dc.identifier.citation	THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35, pp. 10049-10057
dc.identifier.issn	2159-5399
dc.identifier.issn	2374-3468
dc.identifier.uri	http://hdl.handle.net/10453/158371
dc.description.abstract	Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph. As one of the most popular graph-based SSL approaches, the recently proposed Graph Convolutional Networks (GCNs) have gained remarkable progress by combining the sound expressiveness of neural networks with graph structure. Nevertheless, the existing graph-based methods do not directly address the core problem of SSL, \emph{i.e.}, the shortage of supervision, and thus their performances are still very limited. To accommodate this issue, this paper presents a novel GCN-based SSL algorithm which aims to enrich the supervision signals by utilizing both data similarities and graph structure. Firstly, by designing a semi-supervised contrastive loss, the improved node representations can be generated via maximizing the agreement between different views of the same data or the data from the same class. Therefore, the rich unlabeled data and the scarce yet valuable labeled data can jointly provide abundant supervision information for learning discriminative node representations, which helps improve the subsequent classification result. Secondly, the underlying determinative relationship between the input graph topology and data features is extracted as supplementary supervision signals for SSL via using a graph generative loss related to input features. Intensive experimental results on a variety of real-world datasets firmly verify the effectiveness of our algorithm when compared with other state-of-the-art methods.
dc.language	en
dc.publisher	AAAI
dc.relation.ispartof	THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
dc.relation.ispartof	AAAI Conference on Artificial Intelligence / Conference on Innovative Applications of Artificial Intelligence / Symposium on Educational Advances in Artificial Intelligence
dc.relation.ispartofseries	AAAI Conference on Artificial Intelligence
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
dc.type	Conference Proceeding
utslib.citation.volume	35
utslib.location.activity	ELECTR NETWORK
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-06-26T04:02:16Z
pubs.finish-date	2021-02-09
pubs.place-of-publication	USA
pubs.publication-status	Published
pubs.start-date	2021-02-02
pubs.volume	35
dc.location	USA

Abstract:

Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph. As one of the most popular graph-based SSL approaches, the recently proposed Graph Convolutional Networks (GCNs) have gained remarkable progress by combining the sound expressiveness of neural networks with graph structure. Nevertheless, the existing graph-based methods do not directly address the core problem of SSL, \emph{i.e.}, the shortage of supervision, and thus their performances are still very limited. To accommodate this issue, this paper presents a novel GCN-based SSL algorithm which aims to enrich the supervision signals by utilizing both data similarities and graph structure. Firstly, by designing a semi-supervised contrastive loss, the improved node representations can be generated via maximizing the agreement between different views of the same data or the data from the same class. Therefore, the rich unlabeled data and the scarce yet valuable labeled data can jointly provide abundant supervision information for learning discriminative node representations, which helps improve the subsequent classification result. Secondly, the underlying determinative relationship between the input graph topology and data features is extracted as supplementary supervision signals for SSL via using a graph generative loss related to input features. Intensive experimental results on a variety of real-world datasets firmly verify the effectiveness of our algorithm when compared with other state-of-the-art methods.

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

http://hdl.handle.net/10453/158371