#machine learning
Feb 2026
Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
FoSTA (Forest-guided Semantic Transport Alignment), which learns supervised forest geometries independently within each domain and uses their shared class-semantic structure to infer cross-domain correspondences without predefined anchors through scalable hierarchical transport.
Adrien Aumon, Myriam Lizotte, Guy Wolf et al.
· arXiv.org · 0 citations