# FlipTest: Fairness Testing via Optimal Transport

arXiv: https://arxiv.org/abs/1906.09218 · HTML: https://mlsanity.com/paper/1906.09218/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2019.

## Built on by (most cited first, 30 of 51)

- [A Clarification of the Nuances in the Fairness Metrics Landscape](https://mlsanity.com/paper/2106.00467/) (2021)
- [Plugin Estimation of Smooth Optimal Transport Maps](https://mlsanity.com/paper/2107.12364/) (2021)
- [NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification](https://mlsanity.com/paper/2112.13214/) (2021)
- [Transport-based Counterfactual Models](https://mlsanity.com/paper/2108.13025/) (2021)
- [Testing Group Fairness via Optimal Transport Projections](https://mlsanity.com/paper/2106.01070/) (2021)
- [Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing](https://mlsanity.com/paper/2305.11602/) (2023)
- [Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud](https://mlsanity.com/paper/2109.03285/) (2021)
- [An improved central limit theorem and fast convergence rates for entropic transportation costs](https://mlsanity.com/paper/2204.09105/) (2022)
- [Removing biased data to improve fairness and accuracy](https://mlsanity.com/paper/2102.03054/) (2021)
- [A Critical Survey on Fairness Benefits of Explainable AI](https://mlsanity.com/paper/2310.13007/) (2023)
- [Counterfactual Fairness Is Basically Demographic Parity](https://mlsanity.com/paper/2208.03843/) (2022)
- [From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing](https://mlsanity.com/paper/2410.04772/) (2024)
- [FairCanary: Rapid Continuous Explainable Fairness](https://mlsanity.com/paper/2106.07057/) (2021)
- [PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks](https://mlsanity.com/paper/2402.02629/) (2024)
- [Fairness Aware Counterfactuals for Subgroups](https://mlsanity.com/paper/2306.14978/) (2023)
- [Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Difference](https://mlsanity.com/paper/2302.11944/) (2023)
- [OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport](https://mlsanity.com/paper/2403.02372/) (2024)
- [Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools](https://mlsanity.com/paper/2309.17337/) (2023)
- [Unified Shapley Framework to Explain Prediction Drift](https://mlsanity.com/paper/2102.07862/) (2021)
- [FairBalance: How to Achieve Equalized Odds With Data Pre-processing](https://mlsanity.com/paper/2107.08310/) (2021)
- [Explainable Global Fairness Verification of Tree-Based Classifiers](https://mlsanity.com/paper/2209.13179/) (2022)
- [Fairness and Sequential Decision Making: Limits, Lessons, and Opportunities](https://mlsanity.com/paper/2301.05753/) (2023)
- [GAN Estimation of Lipschitz Optimal Transport Maps](https://mlsanity.com/paper/2202.07965/) (2022)
- [Locating disparities in machine learning](https://mlsanity.com/paper/2208.06680/) (2022)
- [Group-blind optimal transport to group parity and its constrained variants](https://mlsanity.com/paper/2310.11407/) (2023)
- [Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness](https://mlsanity.com/paper/2408.03425/) (2024)
- [Counterfactual Multi-Token Fairness in Text Classification](https://mlsanity.com/paper/2202.03792/) (2022)
- [Mitigating Source Bias for Fairer Weak Supervision](https://mlsanity.com/paper/2303.17713/) (2023)
- [Fair-CDA: Continuous and Directional Augmentation for Group Fairness](https://mlsanity.com/paper/2304.00295/) (2023)
- [Human-in-the-loop Fairness: Integrating Stakeholder Feedback to Incorporate Fairness Perspectives in Responsible AI](https://mlsanity.com/paper/2312.08064/) (2023)

## Abstract (arXiv)

We present FlipTest, a black-box technique for uncovering discrimination in classifiers. FlipTest is motivated by the intuitive question: had an individual been of a different protected status, would the model have treated them differently? Rather than relying on causal information to answer this question, FlipTest leverages optimal transport to match individuals in different protected groups, creating similar pairs of in-distribution samples. We show how to use these instances to detect discrimination by constructing a "flipset": the set of individuals whose classifier output changes post-translation, which corresponds to the set of people who may be harmed because of their group membership. To shed light on why the model treats a given subgroup differently, FlipTest produces a "transparency report": a ranking of features that are most associated with the model's behavior on the flipset. Evaluating the approach on three case studies, we show that this provides a computationally inexpensive way to identify subgroups that may be harmed by model discrimination, including in cases where the model satisfies group fairness criteria.