GoGNN: Graph of graphs neural network for predicting structured entity interactions

Wang, H; Lian, D; Zhang, Y; Qin, L; Lin, X

GoGNN: Graph of graphs neural network for predicting structured entity interactions

Wang, H Lian, D Zhang, Y

Qin, L

Lin, X

Permalink

Publisher:: International Joint Conferences on Artificial Intelligence Organization
Publication Type:: Journal Article
Citation:: IJCAI : proceedings of the conference / sponsored by the International Joint Conferences on Artificial Intelligence, 2021, 2021-January, pp. 1317-1323
Issue Date:: 2021-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (1.11 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, H
dc.contributor.author	Lian, D
dc.contributor.author	Zhang, Y https://orcid.org/0000-0002-2674-1638
dc.contributor.author	Qin, L https://orcid.org/0000-0001-6068-5062
dc.contributor.author	Lin, X
dc.date.accessioned	2022-01-31T04:30:57Z
dc.date.available	2022-01-31T04:30:57Z
dc.date.issued	2021-01-01
dc.identifier.citation	IJCAI : proceedings of the conference / sponsored by the International Joint Conferences on Artificial Intelligence, 2021, 2021-January, pp. 1317-1323
dc.identifier.isbn	9780999241165
dc.identifier.issn	1045-0823
dc.identifier.uri	http://hdl.handle.net/10453/153938
dc.description.abstract	© 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved. Entity interaction prediction is essential in many important applications such as chemistry, biology, material science, and medical science. The problem becomes quite challenging when each entity is represented by a complex structure, namely structured entity, because two types of graphs are involved: local graphs for structured entities and a global graph to capture the interactions between structured entities. We observe that existing works on structured entity interaction prediction cannot properly exploit the unique graph of graphs model. In this paper, we propose a Graph of Graphs Neural Network, namely GoGNN, which extracts the features in both structured entity graphs and the entity interaction graph in a hierarchical way. We also propose the dual-attention mechanism that enables the model to preserve the neighbor importance in both levels of graphs. Extensive experiments on real-world datasets show that GoGNN outperforms the state-of-the-art methods on two representative structured entity interaction prediction tasks: chemical-chemical interaction prediction and drug-drug interaction prediction. Our code is available at Github.
dc.language	en
dc.publisher	International Joint Conferences on Artificial Intelligence Organization
dc.relation.ispartof	IJCAI : proceedings of the conference / sponsored by the International Joint Conferences on Artificial Intelligence
dc.relation.isbasedon	10.24963/ijcai.2020/183
dc.rights	info:eu-repo/semantics/openAccess
dc.title	GoGNN: Graph of graphs neural network for predicting structured entity interactions
dc.type	Journal Article
utslib.citation.volume	2021-January
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 - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	open_access	*
pubs.consider-herdc	false
dc.date.updated	2022-01-31T04:30:56Z
pubs.publication-status	Published
pubs.volume	2021-January

Abstract:

© 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved. Entity interaction prediction is essential in many important applications such as chemistry, biology, material science, and medical science. The problem becomes quite challenging when each entity is represented by a complex structure, namely structured entity, because two types of graphs are involved: local graphs for structured entities and a global graph to capture the interactions between structured entities. We observe that existing works on structured entity interaction prediction cannot properly exploit the unique graph of graphs model. In this paper, we propose a Graph of Graphs Neural Network, namely GoGNN, which extracts the features in both structured entity graphs and the entity interaction graph in a hierarchical way. We also propose the dual-attention mechanism that enables the model to preserve the neighbor importance in both levels of graphs. Extensive experiments on real-world datasets show that GoGNN outperforms the state-of-the-art methods on two representative structured entity interaction prediction tasks: chemical-chemical interaction prediction and drug-drug interaction prediction. Our code is available at Github.

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

http://hdl.handle.net/10453/153938