Temporal dynamics unleashed: Elevating variational graph attention

Soheila Molaei, Ghazaleh Niknam, Ghadeer O. Ghosheh, Vinod Kumar Chauhan, Hadi Zare, Tingting Zhu, Shirui Pan, David A. Clifton

Abstract: Highlights•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.