FAIRWELL modifies the VICReg self-supervised loss to be subject-aware and pooling-based, improving fairness metrics on D-Vlog, MIMIC, and MODMA with minimal performance drop.
Does this paper rely on one or more datasets? (yes/no) yes If yes, please address the following points: 3.2
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
-
FAIRWELL: Fair Multimodal Self-Supervised Learning for Wellbeing Prediction
FAIRWELL modifies the VICReg self-supervised loss to be subject-aware and pooling-based, improving fairness metrics on D-Vlog, MIMIC, and MODMA with minimal performance drop.