Marrying Fairness and Explainability in Supervised Learning

• URL: http://arxiv.org/abs/2204.02947v3
• Date: Fri, 21 Apr 2023 02:49:51 GMT
• Title: Marrying Fairness and Explainability in Supervised Learning
• Authors: Przemyslaw Grabowicz, Nicholas Perello, Aarshee Mishra
• Abstract summary: We formalize direct discrimination as a direct causal effect of the protected attributes on the decisions. We find that state-of-the-art fair learning methods can induce discrimination via association or reverse discrimination. We propose to nullify the influence of the protected attribute on the output of the system, while preserving the influence of remaining features.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning algorithms that aid human decision-making may inadvertently discriminate against certain protected groups. We formalize direct discrimination as a direct causal effect of the protected attributes on the decisions, while induced discrimination as a change in the causal influence of non-protected features associated with the protected attributes. The measurements of marginal direct effect (MDE) and SHapley Additive exPlanations (SHAP) reveal that state-of-the-art fair learning methods can induce discrimination via association or reverse discrimination in synthetic and real-world datasets. To inhibit discrimination in algorithmic systems, we propose to nullify the influence of the protected attribute on the output of the system, while preserving the influence of remaining features. We introduce and study post-processing methods achieving such objectives, finding that they yield relatively high model accuracy, prevent direct discrimination, and diminishes various disparity measures, e.g., demographic disparity.

Related papers

• 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. We show that enforcing a causal constraint often reduces the disparity between demographic groups. We introduce a new neural approach for causally-constrained fair learning.
  arXiv  Detail & Related papers  (2024-05-24T11:19:52Z)
• Unlawful Proxy Discrimination: A Framework for Challenging Inherently Discriminatory Algorithms [4.1221687771754]
  EU legal concept of direct discrimination may apply to various algorithmic decision-making contexts. Unlike indirect discrimination, there is generally no 'objective justification' stage in the direct discrimination framework. We focus on the most likely candidate for direct discrimination in the algorithmic context.
  arXiv  Detail & Related papers  (2024-04-22T10:06:17Z)
• Thinking Outside the Box: Orthogonal Approach to Equalizing Protected Attributes [6.852292115526837]
  Black box AI may exacerbate health-related disparities and biases in clinical decision-making. This work proposes a machine learning-based approach aiming to analyze and suppress the effect of the confounder.
  arXiv  Detail & Related papers  (2023-11-21T13:48:56Z)
• Causal Fair Machine Learning via Rank-Preserving Interventional Distributions [0.5062312533373299]
  We define individuals as being normatively equal if they are equal in a fictitious, normatively desired (FiND) world. We propose rank-preserving interventional distributions to define a specific FiND world in which this holds. We show that our warping approach effectively identifies the most discriminated individuals and mitigates unfairness.
  arXiv  Detail & Related papers  (2023-07-24T13:46:50Z)
• Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions [13.279926364884512]
  Machine learning models can underperform on certain population groups due to choices made during model development and bias inherent in the data. We quantify aleatoric discrimination by determining the performance limits of a model under fairness constraints. We quantify epistemic discrimination as the gap between a model's accuracy when fairness constraints are applied and the limit posed by aleatoric discrimination.
  arXiv  Detail & Related papers  (2023-01-27T15:38:20Z)
• Fairness via Adversarial Attribute Neighbourhood Robust Learning [49.93775302674591]
  We propose a principled underlineRobust underlineAdversarial underlineAttribute underlineNeighbourhood (RAAN) loss to debias the classification head.
  arXiv  Detail & Related papers  (2022-10-12T23:39:28Z)
• Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation [55.27563366506407]
  We introduce a discriminator-free adversarial learning network (DALN) for unsupervised domain adaptation (UDA) DALN achieves explicit domain alignment and category distinguishment through a unified objective. DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets.
  arXiv  Detail & Related papers  (2022-04-08T04:40:18Z)
• 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)
• Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach [54.32266555843765]
  This paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors. The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints.
  arXiv  Detail & Related papers  (2020-09-26T10:50:33Z)
• Discrimination of POVMs with rank-one effects [62.997667081978825]
  This work provides an insight into the problem of discrimination of positive operator valued measures with rank-one effects. We compare two possible discrimination schemes: the parallel and adaptive ones. We provide an explicit algorithm which allows us to find this adaptive scheme.
  arXiv  Detail & Related papers  (2020-02-13T11:34:50Z)
• Learning from Discriminatory Training Data [2.1869017389979266]
  Supervised learning systems are trained using historical data and, if the data was tainted by discrimination, they may unintentionally learn to discriminate against protected groups. We propose that fair learning methods, despite training on potentially discriminatory datasets, shall perform well on fair test datasets.
  arXiv  Detail & Related papers  (2019-12-17T18:53:23Z)

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.