# Interpretable and Fair Mechanisms for Abstaining Classifiers

arXiv: https://arxiv.org/abs/2503.18826 · HTML: https://mlsanity.com/paper/2503.18826/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 20 of 20)

- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [An Intersectional Definition of Fairness](https://mlsanity.com/paper/1807.08362/) (2018)
- [Self-Adaptive Training: beyond Empirical Risk Minimization](https://mlsanity.com/paper/2002.10319/) (2020)
- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning](https://mlsanity.com/paper/1904.05419/) (2019)
- [Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI](https://mlsanity.com/paper/2005.05906/) (2020)
- [Optimal strategies for reject option classifiers](https://mlsanity.com/paper/2101.12523/) (2021)
- [Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation](https://mlsanity.com/paper/2205.04610/) (2022)
- [Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem](https://mlsanity.com/paper/2310.02521/) (2023)
- [Selective Classification via One-Sided Prediction](https://mlsanity.com/paper/2010.07853/) (2020)
- [Selective Classification Can Magnify Disparities Across Groups](https://mlsanity.com/paper/2010.14134/) (2020)
- [Selective Regression Under Fairness Criteria](https://mlsanity.com/paper/2110.15403/) (2021)
- [Classification with abstention but without disparities](https://mlsanity.com/paper/2102.12258/) (2021)
- [AUC-based Selective Classification](https://mlsanity.com/paper/2210.10703/) (2022)
- [Deep Neural Network Benchmarks for Selective Classification](https://mlsanity.com/paper/2401.12708/) (2024)
- ["Even if ..." -- Diverse Semifactual Explanations of Reject](https://mlsanity.com/paper/2207.01898/) (2022)
- [Unsupervised Anomaly Detection with Rejection](https://mlsanity.com/paper/2305.13189/) (2023)
- [Explaining Reject Options of Learning Vector Quantization Classifiers](https://mlsanity.com/paper/2202.07244/) (2022)
- [WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts](https://mlsanity.com/paper/2310.18724/) (2023)

## Built on by (most cited first, 2 of 2)

- [Bounded-Abstention Pairwise Learning to Rank](https://mlsanity.com/paper/2505.23437/) (2025)
- [Towards Provably Fair Machine Learning: Bayesian Approaches For Consistent and Transparent Predictions](https://mlsanity.com/paper/2606.12615/) (2026)

## Abstract (arXiv)

Abstaining classifiers have the option to refrain from providing a prediction for instances that are difficult to classify. The abstention mechanism is designed to trade off the classifier's performance on the accepted data while ensuring a minimum number of predictions. In this setting, often fairness concerns arise when the abstention mechanism solely reduces errors for the majority groups of the data, resulting in increased performance differences across demographic groups. While there exist a bunch of methods that aim to reduce discrimination when abstaining, there is no mechanism that can do so in an explainable way. In this paper, we fill this gap by introducing Interpretable and Fair Abstaining Classifier IFAC, an algorithm that can reject predictions both based on their uncertainty and their unfairness. By rejecting possibly unfair predictions, our method reduces error and positive decision rate differences across demographic groups of the non-rejected data. Since the unfairness-based rejections are based on an interpretable-by-design method, i.e., rule-based fairness checks and situation testing, we create a transparent process that can empower human decision-makers to review the unfair predictions and make more just decisions for them. This explainable aspect is especially important in light of recent AI regulations, mandating that any high-risk decision task should be overseen by human experts to reduce discrimination risks.