Structural and node-level augmentations for graph anomalies.

<p>Left: original attributed network <i>G</i>. Right: augmented attributed network . Middle: augmentation methods: (1) feature copying (attribute mimicking across distant nodes); (2) feature scaling (multiplying or dividing continuous attributes); (3) node isolation (dropping all i...

Full description

Saved in:
Bibliographic Details
Main Author: Hossein Rafieizadeh (22676722) (author)
Other Authors: Hadi Zare (20073000) (author), Mohsen Ghassemi Parsa (22676725) (author), Hocine Cherifi (8177628) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849927641084198912
author Hossein Rafieizadeh (22676722)
author2 Hadi Zare (20073000)
Mohsen Ghassemi Parsa (22676725)
Hocine Cherifi (8177628)
author2_role author
author
author
author_facet Hossein Rafieizadeh (22676722)
Hadi Zare (20073000)
Mohsen Ghassemi Parsa (22676725)
Hocine Cherifi (8177628)
author_role author
dc.creator.none.fl_str_mv Hossein Rafieizadeh (22676722)
Hadi Zare (20073000)
Mohsen Ghassemi Parsa (22676725)
Hocine Cherifi (8177628)
dc.date.none.fl_str_mv 2025-11-24T18:37:54Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0335135.g003
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Structural_and_node-level_augmentations_for_graph_anomalies_/30698008
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Cell Biology
Science Policy
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
intrusions across social
reconstructions across views
level contrastive learning
dual contrastive learning
across six benchmarks
div >< p
view discrepancies underutilized
augmented graph views
dcor improves auroc
view discrepancies
level contrast
dual autoencoder
augmented view
specific information
six datasets
reduces auroc
publicly available
preserves fine
physical domains
performing non
maximum gain
leaving cross
identifying threats
financial fraud
existing graph
dcor reconstructs
dcor ),
contrasts reconstructions
attributed networks
attribute patterns
dc.title.none.fl_str_mv Structural and node-level augmentations for graph anomalies.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Left: original attributed network <i>G</i>. Right: augmented attributed network . Middle: augmentation methods: (1) feature copying (attribute mimicking across distant nodes); (2) feature scaling (multiplying or dividing continuous attributes); (3) node isolation (dropping all incident edges of selected nodes); (4) random shortcut connections and clique injection (adding shortcuts or small dense cliques across and within communities). Color coding: green nodes are normal; red nodes are augmented (selected for structure or feature augmentations; isolated nodes appear red with no incident edges); gray edges are original connections; orange or red edges indicate injected connections (random shortcuts or clique edges); solid feature bars are original attributes; cross-hatched bars mark augmented features; the thin gray curved arrow in the feature panel indicates attribute copying. Collectively, these augmentations induce structural, attribute, and interaction anomalies, creating cross-view discrepancies leveraged by our reconstruction-level contrast.</p>
eu_rights_str_mv openAccess
id Manara_e45233acdc4781007622c52bf5861738
identifier_str_mv 10.1371/journal.pone.0335135.g003
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30698008
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Structural and node-level augmentations for graph anomalies.Hossein Rafieizadeh (22676722)Hadi Zare (20073000)Mohsen Ghassemi Parsa (22676725)Hocine Cherifi (8177628)Cell BiologyScience PolicyEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedintrusions across socialreconstructions across viewslevel contrastive learningdual contrastive learningacross six benchmarksdiv >< pview discrepancies underutilizedaugmented graph viewsdcor improves aurocview discrepancieslevel contrastdual autoencoderaugmented viewspecific informationsix datasetsreduces aurocpublicly availablepreserves finephysical domainsperforming nonmaximum gainleaving crossidentifying threatsfinancial fraudexisting graphdcor reconstructsdcor ),contrasts reconstructionsattributed networksattribute patterns<p>Left: original attributed network <i>G</i>. Right: augmented attributed network . Middle: augmentation methods: (1) feature copying (attribute mimicking across distant nodes); (2) feature scaling (multiplying or dividing continuous attributes); (3) node isolation (dropping all incident edges of selected nodes); (4) random shortcut connections and clique injection (adding shortcuts or small dense cliques across and within communities). Color coding: green nodes are normal; red nodes are augmented (selected for structure or feature augmentations; isolated nodes appear red with no incident edges); gray edges are original connections; orange or red edges indicate injected connections (random shortcuts or clique edges); solid feature bars are original attributes; cross-hatched bars mark augmented features; the thin gray curved arrow in the feature panel indicates attribute copying. Collectively, these augmentations induce structural, attribute, and interaction anomalies, creating cross-view discrepancies leveraged by our reconstruction-level contrast.</p>2025-11-24T18:37:54ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0335135.g003https://figshare.com/articles/figure/Structural_and_node-level_augmentations_for_graph_anomalies_/30698008CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306980082025-11-24T18:37:54Z
spellingShingle Structural and node-level augmentations for graph anomalies.
Hossein Rafieizadeh (22676722)
Cell Biology
Science Policy
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
intrusions across social
reconstructions across views
level contrastive learning
dual contrastive learning
across six benchmarks
div >< p
view discrepancies underutilized
augmented graph views
dcor improves auroc
view discrepancies
level contrast
dual autoencoder
augmented view
specific information
six datasets
reduces auroc
publicly available
preserves fine
physical domains
performing non
maximum gain
leaving cross
identifying threats
financial fraud
existing graph
dcor reconstructs
dcor ),
contrasts reconstructions
attributed networks
attribute patterns
status_str publishedVersion
title Structural and node-level augmentations for graph anomalies.
title_full Structural and node-level augmentations for graph anomalies.
title_fullStr Structural and node-level augmentations for graph anomalies.
title_full_unstemmed Structural and node-level augmentations for graph anomalies.
title_short Structural and node-level augmentations for graph anomalies.
title_sort Structural and node-level augmentations for graph anomalies.
topic Cell Biology
Science Policy
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
intrusions across social
reconstructions across views
level contrastive learning
dual contrastive learning
across six benchmarks
div >< p
view discrepancies underutilized
augmented graph views
dcor improves auroc
view discrepancies
level contrast
dual autoencoder
augmented view
specific information
six datasets
reduces auroc
publicly available
preserves fine
physical domains
performing non
maximum gain
leaving cross
identifying threats
financial fraud
existing graph
dcor reconstructs
dcor ),
contrasts reconstructions
attributed networks
attribute patterns