A worst-group equalized odds regularizer targets extreme subgroup deviations in true and false positive rates to improve multi-attribute fairness in medical imaging while preserving AUC.
9th International Conference on Learning Representations (2021), https://par.nsf.gov/biblio/10279881
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Worst-Group Equalized Odds Regularization for Multi-Attribute Fair Medical Image Classification
A worst-group equalized odds regularizer targets extreme subgroup deviations in true and false positive rates to improve multi-attribute fairness in medical imaging while preserving AUC.