Fair Pipelines

By Amanda Bower, Sarah Kitchen, Laura Niss, M. Strauss, Alexander Vargas, Suresh Venkatasubramanian. 2017

48 citations recorded by the source corpus.

This work facilitates ensuring fairness of machine learning in the real world by decoupling fairness considerations in compound decisions. In particular, this work studies how fairness propagates through a compound decision-making processes, which we call a pipeline. Prior work in algorithmic fairness only focuses on fairness with respect to one decision. However, many decision-making processes require more than one decision. For instance, hiring is at least a two stage model: deciding who to interview from the applicant pool and then deciding who to hire from the interview pool. Perhaps surprisingly, we show that the composition of fair components may not guarantee a fair pipeline under a $(1+\varepsilon)$-equal opportunity definition of fair. However, we identify circumstances that do provide that guarantee. We also propose numerous directions for future work on more general compound machine learning decisions.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

The Frontiers of Fairness in Machine Learning (2018, background): “There are certain special settings, e.g. the “ﬁltering pipeline” scenario of [BKN + 17] — modeling a scenario in which a job applicant is selected only if she is selected at every stage of the pipeline — in which (multiplicative approximations of) statistical fairness notions compose in a well…”
Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer (2017, unknown): “Bower et al. [4] describe fair sequential decision making but do not have a pass concept or provide a learning procedure.”
Fairness Under Composition (2018, background): “(7)[1] considers what boils down to AND-fairness for Equal Opportunity and presents an excellent collection of evocative example scenarios.”