Interpretable and Fair Mechanisms for Abstaining Classifiers

• URL: http://arxiv.org/abs/2503.18826v2
• Date: Mon, 14 Apr 2025 09:08:36 GMT
• Title: Interpretable and Fair Mechanisms for Abstaining Classifiers
• Authors: Daphne Lenders, Andrea Pugnana, Roberto Pellungrini, Toon Calders, Dino Pedreschi, Fosca Giannotti,
• Abstract summary: We introduce Interpretable and Fair Abstaining, an algorithm that can reject both predictions based on uncertainty and their unfairness.<n>Our method reduces error and positive decision rate differences across demographic groups the non-rejected data.<n>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.
• Score: 12.539170258479778
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Achieving Fairness in Predictive Process Analytics via Adversarial Learning [50.31323204077591]
  This paper addresses the challenge of integrating a debiasing phase into predictive business process analytics. Our framework leverages on adversial debiasing is evaluated on four case studies, showing a significant reduction in the contribution of biased variables to the predicted value.
  arXiv  Detail & Related papers  (2024-10-03T15:56:03Z)
• Conformal Prediction Sets Can Cause Disparate Impact [4.61590049339329]
  We show that providing prediction sets can lead to disparate impact in decisions.<n>We propose to equalize set sizes across groups which empirically leads to lower disparate impact.
  arXiv  Detail & Related papers  (2024-10-02T18:00:01Z)
• Identifying and Mitigating Social Bias Knowledge in Language Models [52.52955281662332]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.<n>FAST surpasses state-of-the-art baselines with superior debiasing performance.<n>This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Fairness-Accuracy Trade-Offs: A Causal Perspective [58.06306331390586]
  We analyze the tension between fairness and accuracy from a causal lens for the first time.<n>We show that enforcing a causal constraint often reduces the disparity between demographic groups.<n>We introduce a new neural approach for causally-constrained fair learning.
  arXiv  Detail & Related papers  (2024-05-24T11:19:52Z)
• Equal Opportunity of Coverage in Fair Regression [50.76908018786335]
  We study fair machine learning (ML) under predictive uncertainty to enable reliable and trustworthy decision-making. We propose Equal Opportunity of Coverage (EOC) that aims to achieve two properties: (1) coverage rates for different groups with similar outcomes are close, and (2) the coverage rate for the entire population remains at a predetermined level.
  arXiv  Detail & Related papers  (2023-11-03T21:19:59Z)
• Counterfactual Reasoning for Bias Evaluation and Detection in a Fairness under Unawareness setting [6.004889078682389]
  Current AI regulations require discarding sensitive features in the algorithm's decision-making process to prevent unfair outcomes. We propose a way to reveal the potential hidden bias of a machine learning model that can persist even when sensitive features are discarded.
  arXiv  Detail & Related papers  (2023-02-16T10:36:18Z)
• A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms [19.86635585740634]
  We present the conceptual idea and a first implementation of a bias-injection sandbox tool to investigate fairness consequences of various biases. Unlike existing toolkits, ours provides a controlled environment to counterfactually inject biases in the ML pipeline. In particular, we can test whether a given remedy can alleviate the injected bias by comparing the predictions resulting after the intervention with true labels in the unbiased regime-that is, before any bias injection.
  arXiv  Detail & Related papers  (2022-04-21T16:12:19Z)
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
  We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
  arXiv  Detail & Related papers  (2021-09-17T13:45:46Z)
• Accounting for Model Uncertainty in Algorithmic Discrimination [16.654676310264705]
  We argue that the fairness approaches should instead focus only on equalizing errors arising due to model uncertainty. We draw a connection between predictive multiplicity and model uncertainty and argue that the techniques from predictive multiplicity could be used to identify errors made due to model uncertainty.
  arXiv  Detail & Related papers  (2021-05-10T10:34:12Z)
• Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty [54.88405167739227]
  We present HAICU, a method for heterogeneous-agent trajectory forecasting that explicitly incorporates agents' class probabilities. We additionally present PUP, a new challenging real-world autonomous driving dataset. We demonstrate that incorporating class probabilities in trajectory forecasting significantly improves performance in the face of uncertainty.
  arXiv  Detail & Related papers  (2021-04-26T10:28:34Z)
• Classification with abstention but without disparities [5.025654873456756]
  We build a general purpose classification algorithm, which is able to abstain from prediction, while avoiding disparate impact. We establish finite sample risk, fairness, and abstention guarantees for the proposed algorithm. Our method empirically shows that moderate abstention rates allow to bypass the risk-fairness trade-off.
  arXiv  Detail & Related papers  (2021-02-24T12:43:55Z)
• The Disparate Impact of Uncertainty: Affirmative Action vs. Affirmative Information [0.0]
  We show that groups with higher average outcomes are typically assigned higher false positive rates. We explain why the intuitive remedy to omit demographic variables from datasets does not correct it. Instead of data omission, this paper examines how data enrichment can broaden access to opportunity.
  arXiv  Detail & Related papers  (2021-02-19T16:40:47Z)
• All of the Fairness for Edge Prediction with Optimal Transport [11.51786288978429]
  We study the problem of fairness for the task of edge prediction in graphs. We propose an embedding-agnostic repairing procedure for the adjacency matrix of an arbitrary graph with a trade-off between the group and individual fairness.
  arXiv  Detail & Related papers  (2020-10-30T15:33:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.