Temporal dynamics unleashed : elevating variational graph attention

Tools

Molaei, Soheila and Niknam, Ghazaleh and Ghosheh, Ghadeer O. and Chauhan, Vinod Kumar and Zare, Hadi and Zhu, Tingting and Pan, Shirui and Clifton, David A. (2024) Temporal dynamics unleashed : elevating variational graph attention. Knowledge-Based Systems, 299. 112110. ISSN 0950-7051 (https://doi.org/10.1016/j.knosys.2024.112110)

[thumbnail of Molaei-etal-KBS-2024-Temporal-dynamics-unleashed]
Preview
 Text. Filename: Molaei-etal-KBS-2024-Temporal-dynamics-unleashed.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (2MB)| Preview

Abstract

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.

ORCID iDs

Molaei, Soheila, Niknam, Ghazaleh, Ghosheh, Ghadeer O., Chauhan, Vinod Kumar ORCID logoORCID: https://orcid.org/0000-0001-8195-548X, Zare, Hadi, Zhu, Tingting, Pan, Shirui and Clifton, David A.;
CORE (COnnecting REpositories)