A novel contrastive multi-view framework for heterogeneous graph embedding

Basit Öğe Kaydı
dc.authorscopusidAsgarali Bouyer / 35177297800
dc.authorwosidAsgarali Bouyer / JOZ-6483-2023
dc.contributor.authorNoori, Azad
dc.contributor.authorBalafar, Mohammad Ali
dc.contributor.authorBouyer, Asgarali
dc.contributor.authorSalmani, Khosro
dc.date.accessioned2025-04-17T14:37:36Z
dc.date.available2025-04-17T14:37:36Z
dc.date.issued2025
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractHeterogeneous graphs, characterized by diverse node types and relational structures, serve as powerful tools for representing intricate real-world systems. Understanding the complex relationships within these graphs is essential for various downstream tasks. However, traditional graph embedding methods often struggle to represent the rich semantics and heterogeneity of these graphs effectively. In order to tackle this challenge, we present an innovative self-supervised multi-view network (SMHGNN) designed for the embedding of heterogeneous graphs. SMHGNN utilizes three complementary views: meta-paths, meta-structures, and the network schema, to thoroughly capture the complex relationships and interactions among nodes in heterogeneous graphs. The proposed SMHGNN utilizes a self-supervised learning paradigm, thereby obviating the necessity for annotated data while simultaneously augmenting the model's capability for generalization. Furthermore, we present an innovative mechanism for the identification of positive and negative samples, which is predicated on a scoring matrix that integrates both node characteristics and graph topology, thereby proficiently differentiating authentic positive pairs from false negatives. Comprehensive empirical evaluations conducted on established benchmark datasets elucidate the enhanced efficacy of our SMHGNN in comparison with cutting-edge methodologies in heterogeneous graph embedding. (The proposed method achieved a 0.75-2.4% improvement in node classification and a 0.78-2.7% improvement in clustering across diverse datasets when compared to previous state-of-the-art methods.).
dc.identifier.citationNoori, A., Balafar, M. A., Bouyer, A., & Salmani, K. (2025). A novel contrastive multi-view framework for heterogeneous graph embedding. Knowledge and Information Systems, 1-27.
dc.identifier.doi10.1007/s10115-025-02346-0
dc.identifier.issn0219-1377
dc.identifier.issn0219-3116
dc.identifier.scopus2-s2.0-85217381254
dc.identifier.scopusqualityQ2
dc.identifier.urihttp://dx.doi.org/10.1007/s10115-025-02346-0
dc.identifier.urihttps://hdl.handle.net/20.500.12713/6304
dc.identifier.wosWOS:001410582900001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorBouyer, Asgarali
dc.institutionauthoridAsgarali Bouyer / 0000-0002-4808-2856
dc.language.isoen
dc.publisherSpringer science and business media deutschland GmbH
dc.relation.ispartofKnowledge and information systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectGraph Neural Networks
dc.subjectHeterogeneous Graph Embedding
dc.subjectMeta-Paths
dc.subjectMeta-Structures
dc.subjectScore Matrix
dc.subjectSelf-Supervised Learning
dc.titleA novel contrastive multi-view framework for heterogeneous graph embedding
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
A-novel-contrastive-multiview-framework-for-heterogeneous-graph-embeddingKnowledge-and-Information-Systems.pdf
Boyut:
1.57 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

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