GCN-RP: Graph Convolutional Network-Based Predictor for Network Connectivity Resilience

Basit Öğe Kaydı
dc.contributor.authorSimsek, Aybike
dc.date.accessioned2026-04-25T14:20:14Z
dc.date.available2026-04-25T14:20:14Z
dc.date.issued2025
dc.departmentSinop Üniversitesi
dc.description.abstractEvaluating the connectivity resilience of real-world networks through attack simulations is a time-consuming process. This study proposes a method that trains Graph Convolutional Networks (GCNs) on synthetic graphs-generated from real graphs-to predict the resilience curves (Normalized Largest Connected Component, NLCC) of real networks. The method was tested on six real-world interaction networks under degree-based and random attack strategies. Results show that GCN achieves Mean Absolute Error (MAE) values between 0.03 and 0.23, with higher accuracy under random attacks. Additionally, the entire process-including synthetic graph generation, attack simulations, and GCN training-takes approximately five times less time than direct simulations on real graphs with similar size and density. These findings demonstrate that the proposed approach offers both accurate and efficient resilience estimation.
dc.identifier.doi10.1109/ACCESS.2025.3647668
dc.identifier.endpage217072
dc.identifier.issn2169-3536
dc.identifier.orcid0000-0002-1033-1597
dc.identifier.scopus2-s2.0-105025940921
dc.identifier.scopusqualityQ1
dc.identifier.startpage217061
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2025.3647668
dc.identifier.urihttps://hdl.handle.net/11486/8442
dc.identifier.volume13
dc.identifier.wosWOS:001651993200009
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorSimsek, Aybike
dc.language.isoen
dc.publisherIeee-Inst Electrical Electronics Engineers Inc
dc.relation.ispartofIeee Access
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20260420
dc.subjectResilience
dc.subjectRobustness
dc.subjectComplex networks
dc.subjectControllability
dc.subjectMeasurement
dc.subjectAccuracy
dc.subjectBiological system modeling
dc.subjectPredictive models
dc.subjectGraph convolutional networks
dc.subjectAdaptation models
dc.subjectgraph neural networks
dc.subjectnetwork resilience
dc.subjectrobustness prediction
dc.titleGCN-RP: Graph Convolutional Network-Based Predictor for Network Connectivity Resilience
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu