The paper introduces paired-consistency, a metric and regularizer that enforces fairness by penalizing models that give different predictions to expert-selected pairs of examples that should be treated alike.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Paired-Consistency: An Example-Based Model-Agnostic Approach to Fairness Regularization in Machine Learning
The paper introduces paired-consistency, a metric and regularizer that enforces fairness by penalizing models that give different predictions to expert-selected pairs of examples that should be treated alike.