SubROC is a new subgroup-discovery method that finds interpretable subpopulations where a binary classifier has unusually high or low ROC/PR AUC, with provably tight search bounds.
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SubROC: AUC-Based Discovery of Exceptional Subgroup Performance for Binary Classifiers
SubROC is a new subgroup-discovery method that finds interpretable subpopulations where a binary classifier has unusually high or low ROC/PR AUC, with provably tight search bounds.