SFNN: A secure and diverse recommender system through graph neural network and regularized variational autoencoder

Basit Öğe Kaydı
dc.authorid0009-0003-7116-5080
dc.authorid0000-0002-8939-1727
dc.authorid0000-0002-7458-8121
dc.authorid0000-0003-1066-740X
dc.authorid0009-0009-5391-9022
dc.authorid0000-0002-4958-4575
dc.contributor.authorBahi, Abderaouf
dc.contributor.authorGasmi, Ibtissem
dc.contributor.authorBentrad, Sassi
dc.contributor.authorAzizi, Mohamed Walid
dc.contributor.authorKhantouchi, Ramzi
dc.contributor.authorUzun-Per, Meryem
dc.date.accessioned2026-01-23T16:53:05Z
dc.date.available2026-01-23T16:53:05Z
dc.date.issued2025
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.descriptionAcknowledgments The authors acknowledge the financial assistance the Algerian Ministry (MESRS) provided for the PRFU Project (PhD Thesis), coded: C00L07UN360120230002. Teşekkür Yazarlar, PRFU Projesi (Doktora Tezi) için Cezayir Bakanlığı (MESRS) tarafından sağlanan mali desteği (kod: C00L07UN360120230002) kabul etmektedir.
dc.description.abstractRecommender systems are frequently improved to filter information and provide users with the most relevant items. However, they face limitations in balancing appropriate and diverse recommendations while ensuring the security and integrity of user data. A new recommender system based on secure fusion neural network is pre sented in this paper. It guarantees data integrity and confidentiality while balancing accuracy and diversity. It integrates a graph neural network that models user-item interactions to improve accuracy, with a regularized variational autoencoder whose evidence lower bound loss function is enhanced by a diversity-promoting regu larization term that favors latent-space dispersion, thereby improving recommendation diversity. To optimize the combination of the two neural networks scores, an adaptive fusion mechanism is introduced to generate final predictions that consider diverse user preferences while maintaining relevance. Furthermore, our approach uses blockchain technology to encrypt and secure data storage, ensuring the integrity and confidentiality of users’ data. The experiments conducted on three datasets show that the proposed model can achieve an accuracy of 78.13 % with an intra-list diversity of 46.82 % for Retail Rocket dataset, an accuracy of 82.44 % with an intra-list diversity of 37.78 % for clothing dataset, and an accuracy of 86.16 % with an intra-list diversity of 47.65 % for MovieLens-1 M dataset.
dc.identifier.citationBahi, A., Gasmi, I., Bentrad, S., Azizi, M. W., Khantouchi, R., & Uzun-Per, M. (2025). SFNN: A secure and diverse recommender system through graph neural network and regularized variational autoencoder. Knowledge-Based Systems, 332, pp. 1-17. https://doi.org/10.1016/j.knosys.2025.114983
dc.identifier.doi10.1016/j.knosys.2025.114983
dc.identifier.endpage17
dc.identifier.issn1872-7409
dc.identifier.issn0950-7051
dc.identifier.scopus2-s2.0-105023170858
dc.identifier.scopusqualityQ1
dc.identifier.startpage1
dc.identifier.urihttps://doi.org/10.1016/j.knosys.2025.114983
dc.identifier.urihttps://hdl.handle.net/20.500.13055/1267
dc.identifier.volume332
dc.identifier.wosWOS:001632333400005
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.indekslendigikaynak.otherSCI-E - Science Citation Index Expanded
dc.institutionauthorUzun-Per, Meryem
dc.institutionauthorid0000-0002-4958-4575
dc.language.isoen
dc.publisherElsevier
dc.relation.ispartofKnowledge-Based Systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectRecommender System
dc.subjectGraph Neural Network
dc.subjectRegularized Variational Autoencoder
dc.subjectData Security
dc.subjectDiversity
dc.subjectBlockchain
dc.titleSFNN: A secure and diverse recommender system through graph neural network and regularized variational autoencoder
dc.typeArticle
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Kapalı Erişim
Ä°sim:
Tam Metin / Full Text.pdf
Boyut:
11.56 MB
Biçim:
Adobe Portable Document Format
Ä°ndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Kapalı Erişim
Ä°sim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
Ä°ndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu