arXiv:2611.13052v1 Announce Type: new Abstract: Output-level fairness does not constrain whether demographic groups rely on similar predictive contributions in representation space. For a nonlinear encoder with a linear head, we show that outcome-conditioned output score disparity equals the signed sum of feature attribution differences across subgroups by allowing small prediction gaps to arise through cancellation effect. We test whether an attribution disparity penalty complements output-level equalized odds based fairness surrogates.
Machine Learning · 2026-11-11
Explanation-Aware Fairness Beyond Output Parity: Joint Output-Attribution Regularization for Medical Image Classification
arXiv:2611.13052v1 Announce Type: new Abstract: Output-level fairness does not constrain whether demographic groups rely on similar predictive contributions in representation space. For a nonlinear encoder with a linear head, we show that outcome-conditioned output score disparity equals the signed sum of feature attribution differences across subgroups by allowing small prediction gaps to arise through cancellation…
Source and attribution
This is an attributed editorial digest. For the complete study and original reporting, follow the source link.
Reader feedback
0 likes · 0 dislikes