DeepSIM: a novel deep learning method for graph similarity computation

dc.citation.issue1
dc.citation.volume28
dc.contributor.authorLiu B
dc.contributor.authorWang Z
dc.contributor.authorZhang J
dc.contributor.authorWu J
dc.contributor.authorQu G
dc.date.accessioned2024-07-30T02:24:03Z
dc.date.available2024-07-30T02:24:03Z
dc.date.issued2024-01
dc.description.abstractAbstract: Graphs are widely used to model real-life information, where graph similarity computation is one of the most significant applications, such as inferring the properties of a compound based on similarity to a known group. Definition methods (e.g., graph edit distance and maximum common subgraph) have extremely high computational cost, and the existing efficient deep learning methods suffer from the problem of inadequate feature extraction which would have a bad effect on similarity computation. In this paper, a double-branch model called DeepSIM was raised to deeply mine graph-level and node-level features to address the above problems. On the graph-level branch, a novel embedding relational reasoning network was presented to obtain interaction between pairwise inputs. Meanwhile, a new local-to-global attention mechanism is designed to improve the capability of CNN-based node-level feature extraction module on another path. In DeepSIM, double-branch outputs will be concatenated as the final feature. The experimental results demonstrate that our methods perform well on several datasets compared to the state-of-the-art deep learning models in related fields.
dc.description.confidentialfalse
dc.edition.editionJanuary 2024
dc.format.pagination61-76
dc.identifier.citationLiu B, Wang Z, Zhang J, Wu J, Qu G. (2024). DeepSIM: a novel deep learning method for graph similarity computation. Soft Computing. 28. 1. (pp. 61-76).
dc.identifier.doi10.1007/s00500-023-09288-1
dc.identifier.eissn1433-7479
dc.identifier.elements-typejournal-article
dc.identifier.issn1432-7643
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/71148
dc.languageEnglish
dc.publisherSpringer-Verlag GmbH
dc.publisher.urihttps://link.springer.com/article/10.1007/s00500-023-09288-1
dc.relation.isPartOfSoft Computing
dc.rights(c) 2023 The Author/s
dc.rightsCC BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectDeep learning
dc.subjectGraph similarity
dc.subjectEmbedding relational reasoning
dc.subjectDouble branch
dc.titleDeepSIM: a novel deep learning method for graph similarity computation
dc.typeJournal article
pubs.elements-id481014
pubs.organisational-groupOther
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Published version.pdf
Size:
2.1 MB
Format:
Adobe Portable Document Format
Description:
481014 PDF.pdf
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
9.22 KB
Format:
Plain Text
Description:
Collections