Achieving Fairness Without Harm via Selective Demographic Experts
This addresses fairness in high-stakes domains like healthcare, where existing methods often harm performance for some groups, though it appears incremental as it builds on group-specific representation learning.
The paper tackles the problem of fairness-accuracy trade-offs in machine learning by proposing a method that learns distinct representations for different demographic groups and selectively applies group-specific experts with a no-harm constraint, achieving fairness without degrading performance across three medical and two face datasets.
As machine learning systems become increasingly integrated into human-centered domains such as healthcare, ensuring fairness while maintaining high predictive performance is critical. Existing bias mitigation techniques often impose a trade-off between fairness and accuracy, inadvertently degrading performance for certain demographic groups. In high-stakes domains like clinical diagnosis, such trade-offs are ethically and practically unacceptable. In this study, we propose a fairness-without-harm approach by learning distinct representations for different demographic groups and selectively applying demographic experts consisting of group-specific representations and personalized classifiers through a no-harm constrained selection. We evaluate our approach on three real-world medical datasets -- covering eye disease, skin cancer, and X-ray diagnosis -- as well as two face datasets. Extensive empirical results demonstrate the effectiveness of our approach in achieving fairness without harm.