The reviewed record of science sign in
Pith

arxiv: 2004.05167 · v1 · pith:H7NJUGPR · submitted 2020-04-12 · cs.CY · cs.LG· stat.ML

Individual Fairness in Pipelines

Reviewed by Pithpith:H7NJUGPRopen to challenge →

classification cs.CY cs.LGstat.ML
keywords fairnesspipelinepipelinesstagesfairunfairnessclassificationcomposition
0
0 comments X
read the original abstract

It is well understood that a system built from individually fair components may not itself be individually fair. In this work, we investigate individual fairness under pipeline composition. Pipelines differ from ordinary sequential or repeated composition in that individuals may drop out at any stage, and classification in subsequent stages may depend on the remaining "cohort" of individuals. As an example, a company might hire a team for a new project and at a later point promote the highest performer on the team. Unlike other repeated classification settings, where the degree of unfairness degrades gracefully over multiple fair steps, the degree of unfairness in pipelines can be arbitrary, even in a pipeline with just two stages. Guided by a panoply of real-world examples, we provide a rigorous framework for evaluating different types of fairness guarantees for pipelines. We show that na\"{i}ve auditing is unable to uncover systematic unfairness and that, in order to ensure fairness, some form of dependence must exist between the design of algorithms at different stages in the pipeline. Finally, we provide constructions that permit flexibility at later stages, meaning that there is no need to lock in the entire pipeline at the time that the early stage is constructed.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Impact of Competition on Outcomes of Score-Based College Admissions

    cs.GT 2026-05 unverdicted novelty 6.0

    A game-theoretic model of admissions with noisy aggregate signals shows counter-intuitive effects: better signal alignment worsens admitted quality under a single university, while competition triggers non-monotonic q...