ReOT uses a theoretically justified locality-aware optimal transport score to identify private classes under extreme label shift and then performs reliable intra-class knowledge transfer while minimizing a generalization bound on target risk.
Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Locality-aware Private Class Identification for Domain Adaptation with Extreme Label Shift
ReOT uses a theoretically justified locality-aware optimal transport score to identify private classes under extreme label shift and then performs reliable intra-class knowledge transfer while minimizing a generalization bound on target risk.