Automated Directed Fairness Testing

1 code implementation • 2 Jul 2018 • Sakshi Udeshi, Pryanshu Arora, Sudipta Chattopadhyay

We show that AEQUITAS effectively generates inputs to uncover fairness violation in all the subject classifiers and systematically improves the fairness of the respective models using the generated test inputs.

BIG-bench Machine Learning Decision Making +1