Help Privacy Policy Disclaimer
  Advanced SearchBrowse





An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision


Lahoti,  Preethi
Databases and Information Systems, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (public)

(Preprint), 9KB

Supplementary Material (public)
There is no public supplementary material available

Wang, H., Grgic-Hlaca, N., Lahoti, P., Gummadi, K. P., & Weller, A. (2019). An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision. Retrieved from https://arxiv.org/abs/1910.10255.

Cite as: http://hdl.handle.net/21.11116/0000-0007-FCD3-F
The notion of individual fairness requires that similar people receive similar treatment. However, this is hard to achieve in practice since it is difficult to specify the appropriate similarity metric. In this work, we attempt to learn such similarity metric from human annotated data. We gather a new dataset of human judgments on a criminal recidivism prediction (COMPAS) task. By assuming the human supervision obeys the principle of individual fairness, we leverage prior work on metric learning, evaluate the performance of several metric learning methods on our dataset, and show that the learned metrics outperform the Euclidean and Precision metric under various criteria. We do not provide a way to directly learn a similarity metric satisfying the individual fairness, but to provide an empirical study on how to derive the similarity metric from human supervisors, then future work can use this as a tool to understand human supervision.