Adjusting CNN emotion-class probabilities by subtracting fitted gender coefficients, one class at a time, reduced male/female true-positive-rate gaps on a FairFace/DeepFace test set without lowering accuracy.
AI Fairness via Domain Adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
While deep learning (DL) approaches are reaching human-level performance for many tasks, including for diagnostics AI, the focus is now on challenges possibly affecting DL deployment, including AI privacy, domain generalization, and fairness. This last challenge is addressed in this study. Here we look at a novel method for ensuring AI fairness with respect to protected or sensitive factors. This method uses domain adaptation via training set enhancement to tackle bias-causing training data imbalance. More specifically, it uses generative models that allow the generation of more synthetic training samples for underrepresented populations. This paper applies this method to the use case of detection of age related macular degeneration (AMD). Our experiments show that starting with an originally biased AMD diagnostics model the method has the ability to improve fairness.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling
Adjusting CNN emotion-class probabilities by subtracting fitted gender coefficients, one class at a time, reduced male/female true-positive-rate gaps on a FairFace/DeepFace test set without lowering accuracy.