# Individual Fairness in Pipelines

arXiv: https://arxiv.org/abs/2004.05167 · HTML: https://mlsanity.com/paper/2004.05167/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2020.

## Built on by (most cited first, 22 of 22)

- [Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness](https://mlsanity.com/paper/2202.08821/) (2022)
- [Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems](https://mlsanity.com/paper/2103.06172/) (2021)
- [Multiaccurate Proxies for Downstream Fairness](https://mlsanity.com/paper/2107.04423/) (2021)
- [Fair Sequential Selection Using Supervised Learning Models](https://mlsanity.com/paper/2110.13986/) (2021)
- [Achieving Counterfactual Fairness for Causal Bandit](https://mlsanity.com/paper/2109.10458/) (2021)
- [Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Making](https://mlsanity.com/paper/2205.04790/) (2022)
- [Fairness-aware Model-agnostic Positive and Unlabeled Learning](https://mlsanity.com/paper/2206.09346/) (2022)
- [Multi Stage Screening: Enforcing Fairness and Maximizing Efficiency in a Pre-Existing Pipeline](https://mlsanity.com/paper/2203.07513/) (2022)
- [Learning Antidote Data to Individual Unfairness](https://mlsanity.com/paper/2211.15897/) (2022)
- [Sequential Strategic Screening](https://mlsanity.com/paper/2301.13397/) (2023)
- [Cascaded Debiasing: Studying the Cumulative Effect of Multiple Fairness-Enhancing Interventions](https://mlsanity.com/paper/2202.03734/) (2022)
- [When Are Two Lists Better than One?: Benefits and Harms in Joint Decision-making](https://mlsanity.com/paper/2308.11721/) (2023)
- [Fair and Optimal Cohort Selection for Linear Utilities](https://mlsanity.com/paper/2102.07684/) (2021)
- [Fairness Through Counterfactual Utilities](https://mlsanity.com/paper/2108.05315/) (2021)
- [Fair Decision-Making for Food Inspections](https://mlsanity.com/paper/2108.05523/) (2021)
- [Towards Fair and Explainable AI using a Human-Centered AI Approach](https://mlsanity.com/paper/2306.07427/) (2023)
- [Towards A Scalable Solution for Improving Multi-Group Fairness in Compositional Classification](https://mlsanity.com/paper/2307.05728/) (2023)
- [Fair Algorithm Design: Fair and Efficacious Machine Scheduling](https://mlsanity.com/paper/2204.06438/) (2022)
- [Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System](https://mlsanity.com/paper/2410.23483/) (2024)
- [FairExpand: Individual Fairness on Graphs with Partial Similarity Information](https://mlsanity.com/paper/2512.18180/) (2025)
- [Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML](https://mlsanity.com/paper/2605.06656/) (2026)
- [Beyond Outcome Gaps: Process-Aware Fairness Diagnosis for LLM-based Multi-Agent Decision Systems](https://mlsanity.com/paper/2609.02092/) (2026)

## Abstract (arXiv)

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"ive 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.