Subgroup choice determines whether bias mitigation helps or hurts, and the minimum KL divergence to the unbiased test distribution predicts success.
A theory of learning from different domains
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Subgroups Matter for Robust Bias Mitigation
Subgroup choice determines whether bias mitigation helps or hurts, and the minimum KL divergence to the unbiased test distribution predicts success.