Abstract
dc:description.abstract<p>Dynamic graph embedding is a key technique for modeling temporal dependencies in evolving networks. While transformer-based models perform well, their quadratic complexity limits scalability on long graph sequences. This thesis compares transformer approaches with the Mamba architecture-a linear-complexity state-space model—for temporal graph embedding.</p><p>Two frameworks are proposed: DG-Mamba and GDG-Mamba. DG-Mamba uses standard GCN-based spatial encoding, while GDG-Mamba incorporates domain-aware edge features using Graph Isomorphism Network with Edge Convolution (GraphGINE). Experiments on UCI, Reality Mining, Slashdot, Bitcoin-OTC, and SBM datasets show that Mamba-based models match or exceed transformer performance, especially on graphs with high temporal variability.</p><p>The thesis also applies GDG-Mamba to PM2.5 forecasting using the KnowAir dataset. Replacing the GRU encoder in PM2.5-GNN with a Mamba-based temporal module improves the model's ability to capture long-range dependencies in pollutant transport.</p><p>These results highlight the scalability and effectiveness of Mamba-based architectures for dynamic graph modeling and environmental forecasting.</p>
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Data Science - (M.S.)
- Discipline thesis:degree_discipline
- Data Science
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Pandey, Ashish
- Contributors dc:contributor
-
- Mengjia Xu
- Ioannis Koutis
- Hai Nhat Phan
Subjects
dc:subject × 8Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.njit.edu/theses/3170