Auditing Predictive Models for Intersectional Biases

• URL: http://arxiv.org/abs/2306.13064v1
• Date: Thu, 22 Jun 2023 17:32:12 GMT
• Title: Auditing Predictive Models for Intersectional Biases
• Authors: Kate S. Boxer, Edward McFowland III, Daniel B. Neill
• Abstract summary: Conditional Bias Scan (CBS) is a flexible auditing framework for detecting intersectional biases in classification models. CBS identifies the subgroup for which there is the most significant bias against the protected class, as compared to the equivalent subgroup in the non-protected class. We show that this methodology can detect previously unidentified intersectional and contextual biases in the COMPAS pre-trial risk assessment tool.
• Score: 1.9346186297861747
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predictive models that satisfy group fairness criteria in aggregate for members of a protected class, but do not guarantee subgroup fairness, could produce biased predictions for individuals at the intersection of two or more protected classes. To address this risk, we propose Conditional Bias Scan (CBS), a flexible auditing framework for detecting intersectional biases in classification models. CBS identifies the subgroup for which there is the most significant bias against the protected class, as compared to the equivalent subgroup in the non-protected class, and can incorporate multiple commonly used fairness definitions for both probabilistic and binarized predictions. We show that this methodology can detect previously unidentified intersectional and contextual biases in the COMPAS pre-trial risk assessment tool and has higher bias detection power compared to similar methods that audit for subgroup fairness.

Related papers

• Finite-Sample and Distribution-Free Fair Classification: Optimal Trade-off Between Excess Risk and Fairness, and the Cost of Group-Blindness [14.421493372559762]
  We quantify the impact of enforcing algorithmic fairness and group-blindness in binary classification under group fairness constraints. We propose a unified framework for fair classification that provides distribution-free and finite-sample fairness guarantees with controlled excess risk.
  arXiv  Detail & Related papers  (2024-10-21T20:04:17Z)
• A structured regression approach for evaluating model performance across intersectional subgroups [53.91682617836498]
  Disaggregated evaluation is a central task in AI fairness assessment, where the goal is to measure an AI system's performance across different subgroups. We introduce a structured regression approach to disaggregated evaluation that we demonstrate can yield reliable system performance estimates even for very small subgroups.
  arXiv  Detail & Related papers  (2024-01-26T14:21:45Z)
• A Universal Unbiased Method for Classification from Aggregate Observations [115.20235020903992]
  This paper presents a novel universal method of CFAO, which holds an unbiased estimator of the classification risk for arbitrary losses. Our proposed method not only guarantees the risk consistency due to the unbiased risk estimator but also can be compatible with arbitrary losses.
  arXiv  Detail & Related papers  (2023-06-20T07:22:01Z)
• Class-Conditional Conformal Prediction with Many Classes [60.8189977620604]
  We propose a method called clustered conformal prediction that clusters together classes having "similar" conformal scores. We find that clustered conformal typically outperforms existing methods in terms of class-conditional coverage and set size metrics.
  arXiv  Detail & Related papers  (2023-06-15T17:59:02Z)
• Statistical Inference for Fairness Auditing [4.318555434063274]
  We frame this task as "fairness auditing," in terms of multiple hypothesis testing. We show how the bootstrap can be used to simultaneously bound performance disparities over a collection of groups. Our methods can be used to flag subpopulations affected by model underperformance, and certify subpopulations for which the model performs adequately.
  arXiv  Detail & Related papers  (2023-05-05T17:54:22Z)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• LOGAN: Local Group Bias Detection by Clustering [86.38331353310114]
  We argue that evaluating bias at the corpus level is not enough for understanding how biases are embedded in a model. We propose LOGAN, a new bias detection technique based on clustering. Experiments on toxicity classification and object classification tasks show that LOGAN identifies bias in a local region.
  arXiv  Detail & Related papers  (2020-10-06T16:42:51Z)
• Fairness with Overlapping Groups [15.154984899546333]
  A standard goal is to ensure the equality of fairness metrics across multiple overlapping groups simultaneously. We reconsider this standard fair classification problem using a probabilistic population analysis. Our approach unifies a variety of existing group-fair classification methods and enables extensions to a wide range of non-decomposable multiclass performance metrics and fairness measures.
  arXiv  Detail & Related papers  (2020-06-24T05:01:10Z)
• Distributional Individual Fairness in Clustering [7.303841123034983]
  We introduce a framework for assigning individuals, embedded in a metric space, to probability distributions over a bounded number of cluster centers. We provide an algorithm for clustering with $p$-norm objective and individual fairness constraints with provable approximation guarantee.
  arXiv  Detail & Related papers  (2020-06-22T20:02:09Z)
• Robust Optimization for Fairness with Noisy Protected Groups [85.13255550021495]
  We study the consequences of naively relying on noisy protected group labels. We introduce two new approaches using robust optimization. We show that the robust approaches achieve better true group fairness guarantees than the naive approach.
  arXiv  Detail & Related papers  (2020-02-21T14:58:37Z)

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.