Yazar "Balafar, Mohammad Ali" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    A novel contrastive multi-view framework for heterogeneous graph embedding
    (Springer science and business media deutschland GmbH, 2025) Noori, Azad; Balafar, Mohammad Ali; Bouyer, Asgarali; Salmani, Khosro
    Heterogeneous 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.).
  • Küçük Resim Yok
    Öğe
    Review of heterogeneous graph embedding methods based on deep learning techniques and comparing their efficiency in node classification
    (Springer Wien, 2024) Noori, Azad; Balafar, Mohammad Ali; Bouyer, Asgarali; Salmani, Khosro
    Graph embedding is an advantageous technique for reducing computational costs and effectively using graph information in machine learning tasks like classification, clustering, and link prediction. As a result, it has become a key method in various research areas. However, different embedding methods may be used depending on the variety of graphs available. One of the most commonly used graph types is the heterogeneous graph (HG) or heterogeneous information network (HIN), which presents unique challenges for graph embedding approaches due to its diverse set of nodes and edges. Several methods have been proposed for heterogeneous graph embedding in recent years to overcome these challenges. This paper aims to review the latest techniques used for this purpose, divided into two main parts: the first part describes the fundamental concepts and obstacles in heterogeneous graph embedding, while the second part compares the most critical methods. Finally, the results are summarized, outlining the challenges and opportunities for future directions.