Temporal dynamics unleashed: Elevating variational graph attention

• Published in: Knowledge-based systems 2024-09, Vol.299, p.None-None, Article 112110
• Main Authors: Molaei, Soheila, Niknam, Ghazaleh, Ghosheh, Ghadeer O., Chauhan, Vinod Kumar, Zare, Hadi, Zhu, Tingting, Pan, Shirui, Clifton, David A.
• Format: Article
• Language: English
• Subjects: Deep generative models; Dynamic graph embedding; Graph attention network; Graph variational neural networks; Markovian assumptions
• ISSN: 0950-7051; 1872-7409
• DOI: 10.1016/j.knosys.2024.112110

This research introduces the Variational Graph Attention Dynamics (VarGATDyn), addressing the complexities of dynamic graph representation learning, where existing models, tailored for static graphs, prove inadequate. VarGATDyn melds attention mechanisms with a Markovian assumption to surpass the challenges of maintaining temporal consistency and the extensive dataset requirements typical of RNN-based frameworks. It harnesses the strengths of the Variational Graph Auto-Encoder (VGAE) framework, Graph Attention Networks (GAT), and Gaussian Mixture Models (GMM) to adeptly navigate the temporal and structural intricacies of dynamic graphs. Through the strategic application of GMMs, the model handles multimodal patterns, thereby rectifying misalignments between prior and estimated posterior distributions. An innovative multiple-learning methodology bolsters the model’s adaptability, leading to an encompassing and effective learning process. Empirical tests underscore VarGATDyn’s dominance in dynamic link prediction across various datasets, highlighting its proficiency in capturing multimodal distributions and temporal dynamics. •Using GMM in VGAE to tackle multimodality and mitigate prior-posterior misalignment.•Innovative VarGATDyn model integrates structural and temporal insights.•Integrating attention mechanisms with Markovian assumptions for dynamic learning.•VarGATDyn iterates learning at each step for robust representation.•Achieves top results in dynamic link prediction on seven datasets.