Fairness Under Feature Exemptions: Counterfactual and Observational Measures

• URL: http://arxiv.org/abs/2006.07986v2
• Date: Fri, 6 Aug 2021 19:27:57 GMT
• Title: Fairness Under Feature Exemptions: Counterfactual and Observational Measures
• Authors: Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover
• Abstract summary: We propose an information-theoretic decomposition of the total disparity into two components. A non-exempt component quantifies the part that cannot be accounted for by the critical features, and an exempt component quantifies the remaining disparity. We perform case studies to show how one can audit/train models while reducing non-exempt disparity.
• Score: 34.5472206536785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the growing use of ML in highly consequential domains, quantifying disparity with respect to protected attributes, e.g., gender, race, etc., is important. While quantifying disparity is essential, sometimes the needs of an occupation may require the use of certain features that are critical in a way that any disparity that can be explained by them might need to be exempted. E.g., in hiring a software engineer for a safety-critical application, coding-skills may be weighed strongly, whereas name, zip code, or reference letters may be used only to the extent that they do not add disparity. In this work, we propose an information-theoretic decomposition of the total disparity (a quantification inspired from counterfactual fairness) into two components: a non-exempt component which quantifies the part that cannot be accounted for by the critical features, and an exempt component that quantifies the remaining disparity. This decomposition allows one to check if the disparity arose purely due to the critical features (inspired from the business necessity defense of disparate impact law) and also enables selective removal of the non-exempt component if desired. We arrive at this decomposition through canonical examples that lead to a set of desirable properties (axioms) that a measure of non-exempt disparity should satisfy. Our proposed measure satisfies all of them. Our quantification bridges ideas of causality, Simpson's paradox, and a body of work from information theory called Partial Information Decomposition. We also obtain an impossibility result showing that no observational measure can satisfy all the desirable properties, leading us to relax our goals and examine observational measures that satisfy only some of them. We perform case studies to show how one can audit/train models while reducing non-exempt disparity.

Related papers

• Identifiability Guarantees for Causal Disentanglement from Purely Observational Data [10.482728002416348]
  Causal disentanglement aims to learn about latent causal factors behind data. Recent advances establish identifiability results assuming that interventions on (single) latent factors are available. We provide a precise characterization of latent factors that can be identified in nonlinear causal models.
  arXiv  Detail & Related papers  (2024-10-31T04:18:29Z)
• 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)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Quantifying Feature Contributions to Overall Disparity Using Information Theory [24.61791450920249]
  When a machine-learning algorithm makes biased decisions, it can be helpful to understand the sources of disparity to explain why the bias exists. We ask the question: what is the "potential" contribution of each individual feature to the observed disparity in the decisions when the exact decision-making mechanism is not accessible? When unable to intervene on the inputs, we quantify the "redundant" statistical dependency about the protected attribute that is present in both the final decision and an individual feature.
  arXiv  Detail & Related papers  (2022-06-16T21:27:22Z)
• Towards efficient representation identification in supervised learning [32.3875659102181]
  Humans have a remarkable ability to disentangle complex sensory inputs. We show theoretically and experimentally that disentanglement is possible even when the auxiliary information dimension is much less than the dimension of the true latent representation.
  arXiv  Detail & Related papers  (2022-04-10T05:34:13Z)
• 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)
• Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap [140.98628848491146]
  We introduce deconfounding scores, which induce better overlap without biasing the target of estimation. We show that deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data. In particular, we show that this technique could be an attractive alternative to standard regularizations.
  arXiv  Detail & Related papers  (2021-04-12T18:50:11Z)
• Fundamental Limits and Tradeoffs in Invariant Representation Learning [99.2368462915979]
  Many machine learning applications involve learning representations that achieve two competing goals. Minimax game-theoretic formulation represents a fundamental tradeoff between accuracy and invariance. We provide an information-theoretic analysis of this general and important problem under both classification and regression settings.
  arXiv  Detail & Related papers  (2020-12-19T15:24:04Z)

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.