Causal Reasoning for Algorithmic Fairness

By Joshua R. Loftus, Chris Russell, Matt J. Kusner, Ricardo M. A. Silva. 2018

147 citations recorded by the source corpus.

In this work, we argue for the importance of causal reasoning in creating fair algorithms for decision making. We give a review of existing approaches to fairness, describe work in causality necessary for the understanding of causal approaches, argue why causality is necessary for any approach that wishes to be fair, and give a detailed analysis of the many recent approaches to causality-based fairness.

Subfields: Artificial Intelligence, Safety Research, Causal Inference & Discovery, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In Causal Inference & Discovery

In AI Ethics, Fairness & Society

Citations in the corpus

A Survey on Bias and Fairness in Machine Learning (2019, methodology): “Domain Sub-domain Reference(s) Data Simpson’s Paradox [68] Machine learning Classification [65] [86] [49] [72] [120] [55] [130] [126] [59] [24] [127] Machine learning Regression [13] [1] Machine learning PCA [111] Machine learning Community detection [85] Machine learning Clustering [30] [7] Machine”
On the Fairness of Causal Algorithmic Recourse (2020, background): “2017a,b), these are sometimes mutually incompatible (Chouldechova 2017), and it has been argued that discrimination, at its heart, corresponds to a (direct or indirect) causal influence of a protected attribute on the prediction, thus making fairness a fundamentally causal problem (Kilbertus et al. ”
Algorithmic Fairness (2020, background): “For a broader review on causal fairness, see [93].”
Interventional Fairness: Causal Database Repair for Algorithmic Fairness (2019, background): “[25, 26] (see also the discussion in [30]) define a classifier as counterfactually fair if the protected attribute of an individual is not a cause of the outcome of the classifier for that individual, i.”
Artificial Intelligence in Human Resources Management: Challenges and a Path Forward (2019, background): “37 Consider how the role of context changes our judgments.”
A Review on Fairness in Machine Learning (2022, background): “One of the common examples that is used to illustrate the importance of causality to identify and mitigate unfairness is the gender bias in Berkeley admission in 1973 [24, 137].”
Making Decisions that Reduce Discriminatory Impacts (2019, unknown): “(4), in general, one requires assumptions that cannot be tested even with randomized controlled trials (Loftus et al., 2018; Kusner et al., 2017).”
The Sensitivity of Counterfactual Fairness to Unmeasured Confounding (2019, unknown): “Loftus et al. (2018) provide further arguments for the importance of causality in fairness as well as a review of existing methods.”