Feature Importance Disparities for Data Bias Investigations

It is widely held that one cause of downstream bias in classifiers is bias present in the training data. Rectifying such biases may involve context-dependent interventions such as training separate models on subgroups, removing features with bias in the collection process, or even conducting real-world experiments to ascertain sources of bias. Despite the need for such data bias investigations, few automated methods exist to assist practitioners in these efforts. In this paper, we present one such method that given a …

bias biases classifiers collection context cs.cy cs.lg data data bias feature features importance investigations process subgroups training training data world