Dual autoencoder with reconstruction-level contrast.

<p>Left: an attributed network <i>G</i> and an augmented view produced by graph data augmentation. Middle: a shared graph-attention encoder yields node embeddings <i>Z</i>, which feed two decoders: a structure decoder reconstructing and an attribute decoder reconstructi...

पूर्ण विवरण

में बचाया:
ग्रंथसूची विवरण
मुख्य लेखक: Hossein Rafieizadeh (22676722) (author)
अन्य लेखक: Hadi Zare (20073000) (author), Mohsen Ghassemi Parsa (22676725) (author), Hocine Cherifi (8177628) (author)
प्रकाशित: 2025
विषय:
टैग: टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
_version_ 1849927640797937664
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 2025-11-24T18:37:56Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0335135.g004
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Dual_autoencoder_with_reconstruction-level_contrast_/30698011
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 Dual autoencoder with reconstruction-level contrast.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Left: an attributed network <i>G</i> and an augmented view produced by graph data augmentation. Middle: a shared graph-attention encoder yields node embeddings <i>Z</i>, which feed two decoders: a structure decoder reconstructing and an attribute decoder reconstructing for the two views, yielding and . Right: reconstruction-level contrast compares, for each node <i>i</i>, the reconstructions via and ; it minimizes <i>D</i> when and , and enforces a learnable margin <i>m</i> when or . Color coding: green nodes denote non-augmented nodes; red nodes denote augmented nodes; the dotted green arc indicates minimization of <i>D</i>; the dashed orange arc indicates margin enforcement; cross-hatched bars mark augmented features; gray edges are neutral; blue heatmaps depict reconstructed matrices.</p>
eu_rights_str_mv openAccess
id Manara_8ee86797d0726b6022710199d67effcd
identifier_str_mv 10.1371/journal.pone.0335135.g004
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30698011
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Dual autoencoder with reconstruction-level contrast.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: an attributed network <i>G</i> and an augmented view produced by graph data augmentation. Middle: a shared graph-attention encoder yields node embeddings <i>Z</i>, which feed two decoders: a structure decoder reconstructing and an attribute decoder reconstructing for the two views, yielding and . Right: reconstruction-level contrast compares, for each node <i>i</i>, the reconstructions via and ; it minimizes <i>D</i> when and , and enforces a learnable margin <i>m</i> when or . Color coding: green nodes denote non-augmented nodes; red nodes denote augmented nodes; the dotted green arc indicates minimization of <i>D</i>; the dashed orange arc indicates margin enforcement; cross-hatched bars mark augmented features; gray edges are neutral; blue heatmaps depict reconstructed matrices.</p>2025-11-24T18:37:56ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0335135.g004https://figshare.com/articles/figure/Dual_autoencoder_with_reconstruction-level_contrast_/30698011CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306980112025-11-24T18:37:56Z
spellingShingle Dual autoencoder with reconstruction-level contrast.
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 Dual autoencoder with reconstruction-level contrast.
title_full Dual autoencoder with reconstruction-level contrast.
title_fullStr Dual autoencoder with reconstruction-level contrast.
title_full_unstemmed Dual autoencoder with reconstruction-level contrast.
title_short Dual autoencoder with reconstruction-level contrast.
title_sort Dual autoencoder with reconstruction-level contrast.
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