U-Fair, a gender-specific uncertainty reweighting for multitask depression detection, improves fairness over an uncertainty baseline but not consistently over unitask or vanilla multitask, and the PHQ-8 difficulty link is weakly supported.
Emer- gent unfairness in algorithmic fairness-accuracy trade-off research
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
-
U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection
U-Fair, a gender-specific uncertainty reweighting for multitask depression detection, improves fairness over an uncertainty baseline but not consistently over unitask or vanilla multitask, and the PHQ-8 difficulty link is weakly supported.