AI RESEARCH
SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective
arXiv CS.LG
•
ArXi:2604.07383v2 Announce Type: replace Cross-city transfer improves prediction in label-scarce cities by leveraging labeled data from other cities, but it becomes challenging when cities adopt incompatible partitions and no ground-truth region correspondences exist. Existing approaches either rely on heuristic region matching, which is often sensitive to anchor choices, or perform distribution-level alignment that leaves correspondences implicit and can be unstable under strong heterogeneity.