A new group-fairness measure matches individuals across protected groups with a transport map, and training under this matching constraint yields fair models with controllable subgroup behavior.
We partition the interval[0,z] into subintervals of length at mostδ
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Fairness Through Matching
A new group-fairness measure matches individuals across protected groups with a transport map, and training under this matching constraint yields fair models with controllable subgroup behavior.