2 papers
cs.LG2025
GCN-TULHOR: Trajectory-User Linking Leveraging GCNs and Higher-Order Spatial Representations
Khoa Tran, Pranav Gupta, Manos Papagelis
Trajectory-user linking (TUL) aims to associate anonymized trajectories with the users who generated them, which is crucial for personalized recommendations, privacy-preserving ana…
cs.LG2025
Fairness and Robustness in Machine Unlearning
Khoa Tran, Simon S. Woo
Machine unlearning poses the challenge of ``how to eliminate the influence of specific data from a pretrained model'' in regard to privacy concerns. While prior research on approxi…