A framework and RL algorithm for long-term fairness under selective labels that decomposes the true fairness measure into observed fairness plus prediction bias and provides sufficient conditions based on predictor confidence.
Elisa , title =
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
-
Long-term Fairness with Selective Labels
A framework and RL algorithm for long-term fairness under selective labels that decomposes the true fairness measure into observed fairness plus prediction bias and provides sufficient conditions based on predictor confidence.