3 papers
cs.LG2026
Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning
Poupak Azad, Cuneyt Gurcan Akcora, Kiarash Shamsi
Temporal graph learning has become essential for analyzing real-world systems whose interactions continuously evolve over time, including financial transaction networks, communicat…
cs.LG2026
LendNova: Towards Automated Credit Risk Assessment with Language Models
Kiarash Shamsi, Danijel Novokmet, Joshua Peters +3
Credit risk assessment is essential in the financial sector, but has traditionally depended on costly feature-based models that often fail to utilize all available information in r…
cs.LG2025
MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs
Kiarash Shamsi, Tran Gia Bao Ngo, Razieh Shirzadkhani +7
Temporal Graph Learning (TGL) has become a robust framework for discovering patterns in dynamic networks and predicting future interactions. While existing research has largely con…