SFGCN: Synergetic fusion-based graph convolutional networks approach for link prediction in social networks

• Published in: Information fusion 2025-02, Vol.114, p.102684, Article 102684
• Main Authors: Lee, Sang-Woong, Tanveer, Jawad, Rahmani, Amir Masoud, Alinejad-Rokny, Hamid, Khoshvaght, Parisa, Zare, Gholamreza, Malekpour Alamdari, Pegah, Hosseinzadeh, Mehdi
• Format: Article
• Language: English
• Subjects: Fusion model; Graph convolutional networks; Graph neural network; Link Prediction; Machine learning; Network data analysis; Social networks
• ISSN: 1566-2535
• DOI: 10.1016/j.inffus.2024.102684

•Proposes a novel Synergetic Fusion-based Graph Convolutional Networks (SFGCN) model for accurate link prediction in social networks.•Utilizes a multi-level fusion mechanism combining structural, textual, and attribute data through early, intermediate, and late fusion strategies.•Outperforms traditional link prediction methods and advanced GCN-based methods across various real-world datasets.•Comprehensive performance metrics, including accuracy, precision, recall, F1-score, and Cohen's Kappa, validate the SFGCN model's predictive capabilities across diverse datasets.•The SFGCN approach uses advanced feature engineering, incorporating multi-modal data to create enriched node and edge representations that capture complex social network interactions. Accurate Link Prediction (LP) in Social Networks (SNs) is crucial for various practical applications, such as recommendation systems and network security. However, traditional techniques often struggle to capture the intricate and multidimensional nature of these networks. This paper presents a novel approach, the Synergetic Fusion-based Graph Convolutional Networks (SFGCN), designed to enhance LP accuracy in SNs. The SFGCN model utilizes a fusion architecture that combines structural features and other attribute data through early, intermediate, and late fusion mechanisms to create improved node and edge representations. We thoroughly evaluate our SFGCN model on seven real-world datasets, encompassing citation networks, co-purchase networks, and academic publication domains. The results demonstrate its superiority over baseline GCN architectures and other selected LP methods, achieving a 6.88 % improvement in accuracy. The experiments show that our model captures the complex interactions and dependencies within SNs, providing a comprehensive understanding of their underlying dynamics. The approach mentioned can be effectively applied in the domain of SN analysis to enhance the accuracy of LP results. This method not only improves the precision of predictions but also enhances the adaptability of the model in diverse SN scenarios.