Maximum Subgroup Discrepancy is a sample-efficient, interpretable distribution distance for intersectional bias detection, provably linear in the number of protected attributes and computable to global optimality via mixed-integer optimization.
Zhang, Federica Sarro, and Mark Harman
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.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Bias Detection via Maximum Subgroup Discrepancy
Maximum Subgroup Discrepancy is a sample-efficient, interpretable distribution distance for intersectional bias detection, provably linear in the number of protected attributes and computable to global optimality via mixed-integer optimization.