Impartial Predictive Modeling: Ensuring Fairness in Arbitrary Models

By Kory D. Johnson, Dean Phillips Foster, Robert A. Stine. 2016

37 citations recorded by the source corpus.

Subfields: 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 AI Ethics, Fairness & Society

Citations in the corpus

Counterfactual Fairness (2017, background): “Following the motivation of IF and [15], we propose that knowledge about relationships between all attributes should be taken into consideration, even if strong assumptions are necessary.”
Fair Regression: Quantitative Definitions and Reduction-based Algorithms (2019, methodology): “Calders et al. (2013), Johnson et al. (2016) and Komiyama et al. (2018) consider a more limited form of independence, expressed via a small number of moment constraints, such as lack of correlation, and design speciﬁc algorithms for linear least squares.”
A Convex Framework for Fair Regression (2017, background): “More recently Johnson et al. [16] also studied fairness for regression problems and formalized several notions for impartial estimates based on the causal relationship between sensitive attributes , legitimate attributes , suspect attributes and the label.”
A Reductions Approach to Fair Classification (2018, methodology): “Copyright 2018 by the author(s). methods, often by relaxing the desired deﬁnitions of fairness, and only enforcing weaker constraints, such as lack of correlation (e.g., Woodworth et al., 2017; Zafar et al., 2017; Johnson et al., 2016; Kamishima et al., 2011; Donini et al., 2018).”
Fairness in Machine Learning (2020, methodology): “…and designing ML systems [2, 7, 14, 15, 21, 22, 23, 25, 28, 29, 31, 34, 44, 45, 46, 52, 53, 54, 55, 56, 59, 66, 69, 71, 72, 73, 74, 75, 82, 84, 87, 89, 90, 94, 95, 97, 98, 99, 103, 104, 106, 114, 115, 116, 121, 123, 126, 138, 139, 141, 148, 149, 153, 156, 159, 165, 174, 176, 177, 178, 179,…”
Optimized Pre-Processing for Discrimination Prevention (2017, background): “Recent definitions of fairness that seek to mitigate this issue include [Johnson et al., 2016] and [Kusner et al.”
Fairness in Machine Learning: A Survey (2020, background): “Directed acyclic graphs (DAGs) are a common means to represent conditional independence assumptions between variables [155].”
The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning (2018, background): “…anti-classiﬁcation requires that: Some authors have suggested stronger notions of anti-classiﬁcation that aim to guard against the use of unprotected traits that are proxies for protected attributes (Bonchi et al., 2017; Grgic-Hlaca et al., 2016; Johnson et al., 2016; Qureshi et al., 2016).”
The Disparate Effects of Strategic Manipulation (2018, background): “Much of the previous work in algorithmic fairness has examined a particular undesirable proxy eect in which a classier’s features may be linked to socially signicant and legally protected attributes like race and gender, interpreting correlations that have arisen due to centuries of accumulated disa”