Debias-CLR uses contrastive learning with class-average counterfactual examples to reduce gender and ethnicity bias in clinical text and vital-sign embeddings, as measured by a modified SC-WEAT score.
Wasserstein Fair Classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose an approach to fair classification that enforces independence between the classifier outputs and sensitive information by minimizing Wasserstein-1 distances. The approach has desirable theoretical properties and is robust to specific choices of the threshold used to obtain class predictions from model outputs. We introduce different methods that enable hiding sensitive information at test time or have a simple and fast implementation. We show empirical performance against different fairness baselines on several benchmark fairness datasets.
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Debias-CLR: A Contrastive Learning Based Debiasing Method for Algorithmic Fairness in Healthcare Applications
Debias-CLR uses contrastive learning with class-average counterfactual examples to reduce gender and ethnicity bias in clinical text and vital-sign embeddings, as measured by a modified SC-WEAT score.