Can I read Concealing Model Unfairness in AI on EtoBox?

Concealing Model Unfairness in AI by Fahim Hasan Alif is a document available to read on EtoBox.

What is Concealing Model Unfairness in AI about?

This document summarizes a research paper that proposes a method for modifying machine learning models to conceal unfairness from multiple explanation methods. The key points are: 1) The researchers demonstrate that it is possible to modify a pre-trained model to manipulate the output of popular feature importance explanation methods with little change in model accuracy. 2) Specifically, their method trains a model to downgrade the apparent importance of a sensitive feature, such as gender or race, accor

Author

Fahim Hasan Alif

Language

EN