TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.
Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics (ACL) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TILT: Target-induced loss tilting under covariate shift
TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.