Study Finds Fairness Interventions Can Shift Disparities Across Sensitive Attributes
A new paper examines how fairness interventions targeting one sensitive attribute in binary classification can create externalities affecting other attributes when multiple sensitive attributes are present.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-13 05:00 · arXiv stat.ML
Robbing Peter to Pay Paul: Cross-Attribute Externalities of Fairness Interventions