Fairness of Classifiers in the Presence of Constraints between Features

• URL: http://arxiv.org/abs/2605.00592v1
• Date: Fri, 01 May 2026 11:58:18 GMT
• Title: Fairness of Classifiers in the Presence of Constraints between Features
• Abstract summary: In Machine Learning, an accepted definition of fairness of a decision is that it should not depend on protected features, such as gender.<n>We define a fair explanation as a prime-implicant reason for the decision that does not contain any protected feature.<n>Surprisingly, ignoring constraints can completely change the fairness of a decision.
• Score: 1.160208922584163
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In Machine Learning, an accepted definition of fairness of a decision taken by a classifier is that it should not depend on protected features, such as gender. Unfortunately, when constraints exist between features, such dependencies can be obscured by the constraints. To avoid this problem, we propose that a decision be considered fair if it has a fair explanation. We define a fair explanation as a prime-implicant reason for the decision that does not contain any protected feature (where the constraints are taken into account in the definition of prime-implicant). Surprisingly, ignoring constraints can completely change the fairness of a decision (according to this definition) even in the absence of constraints between protected and unprotected features. Three possible definitions of fairness of a classifier are that for all its decisions (1) there are only fair explanations, (2) there is at least one fair explanation, or (3) changing protected features does not change the outcome. We identify the relationships between these different definitions of fairness and study the computational complexity of testing fairness of classifiers.

Related papers

• Counterfactual Explanations and the Scope of Contestability [0.0]
  This paper is about how agency can be reinstated by the provision of certain kinds of knowledge.<n>We discuss whether a specific type of explanation, counterfactual explanations, facilitates our ability to contest algorithmic decisions.
  arXiv  Detail & Related papers  (2026-08-25T13:45:16Z)
• 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)
• What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning [52.51430732904994]
  In reinforcement learning problems, agents must consider long-term fairness while maximizing returns. Recent works have proposed many different types of fairness notions, but how unfairness arises in RL problems remains unclear. We introduce a novel notion called dynamics fairness, which explicitly captures the inequality stemming from environmental dynamics.
  arXiv  Detail & Related papers  (2024-04-16T22:47:59Z)
• Differential Parity: Relative Fairness Between Two Sets of Decisions [4.106941784309168]
  We propose to test the relative fairness of one decision set against another with differential parity.<n>It avoids the ambiguous and contradictory definition of absolutely'' fair decisions.<n>It reveals the relative preference and bias between two decision sets.
  arXiv  Detail & Related papers  (2021-12-21T15:05:42Z)
• Nested Counterfactual Identification from Arbitrary Surrogate Experiments [95.48089725859298]
  We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
  arXiv  Detail & Related papers  (2021-07-07T12:51:04Z)
• Sufficient reasons for classifier decisions in the presence of constraints [9.525900373779395]
  Recent work has unveiled a theory for reasoning about the decisions made by binary classifiers. We propose a more general theory, tailored to taking constraints into account. We prove that this simple idea results in reasons that are no less (and sometimes more) succinct.
  arXiv  Detail & Related papers  (2021-05-12T23:36:12Z)
• Contrastive Explanations for Model Interpretability [77.92370750072831]
  We propose a methodology to produce contrastive explanations for classification models. Our method is based on projecting model representation to a latent space. Our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.
  arXiv  Detail & Related papers  (2021-03-02T00:36:45Z)
• A Weaker Faithfulness Assumption based on Triple Interactions [89.59955143854556]
  We propose a weaker assumption that we call $2$-adjacency faithfulness. We propose a sound orientation rule for causal discovery that applies under weaker assumptions.
  arXiv  Detail & Related papers  (2020-10-27T13:04:08Z)
• Algorithmic Decision Making with Conditional Fairness [48.76267073341723]
  We define conditional fairness as a more sound fairness metric by conditioning on the fairness variables. We propose a Derivable Conditional Fairness Regularizer (DCFR) to track the trade-off between precision and fairness of algorithmic decision making.
  arXiv  Detail & Related papers  (2020-06-18T12:56:28Z)
• Fair Inputs and Fair Outputs: The Incompatibility of Fairness in Privacy and Accuracy [0.0]
  We argue that privacy and need-to-know are desirable properties of a decision system. We show that for an optimal classifier these three properties are in general incompatible. We provide an algorithm to verify if the trade-off between the three properties exists in a given dataset.
  arXiv  Detail & Related papers  (2020-05-19T04:32:16Z)
• Abstracting Fairness: Oracles, Metrics, and Interpretability [21.59432019966861]
  We examine what can be learned from a fairness oracle equipped with an underlying understanding of true'' fairness. Our results have implications for interpretablity -- a highly desired but poorly defined property of classification systems.
  arXiv  Detail & Related papers  (2020-04-04T03:14:53Z)
• The Measure and Mismeasure of Fairness [6.6697126372463345]
  We argue that the equitable design of algorithms requires grappling with their context-specific consequences. We offer strategies to ensure algorithms are better aligned with policy goals.
  arXiv  Detail & Related papers  (2018-07-31T18:38:04Z)

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.