A new active learning algorithm, FCCM, maximizes factual and counterfactual coverage and reduces treatment effect estimation error under limited labeling budgets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspective
A new active learning algorithm, FCCM, maximizes factual and counterfactual coverage and reduces treatment effect estimation error under limited labeling budgets.