A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual &Group Unfairness via Inequality Indices

By Till Speicher, Hoda Heidari, Nina Grgic-Hlaca, Krishna P. Gummadi, Adish Kumar Singla, Adrian Weller, Muhammad Bilal Zafar. 2018

300 citations recorded by the source corpus.

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine which of the two is more unfair? Our core idea is to use existing inequality indices from economics to measure how unequally the outcomes of an algorithm benefit different individuals or groups in a population. Our work offers a justified and general framework to compare and contrast the (un)fairness of algorithmic predictors. This unifying approach enables us to quantify unfairness both at the individual and the group level. Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component. Earlier methods are typically designed to tackle only between-group un- fairness, which may be justified for legal or other reasons. However, we demonstrate that minimizing exclusively the between-group component may, in fact, increase the within-group, and hence the overall unfairness. We characterize and illustrate the tradeoffs between our measures of (un)fairness and the prediction accuracy.

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

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Another possible metric is the Theil index [394] , which measures inequality both in terms of individual and group fairness.”
Fairness without Demographics through Adversarially Reweighted Learning (2020, background): “There is also a large body of work on incorporating these fairness notions into ML models, including learning better representations [56, 38, 37] and adding fairness constraints in the learning objective [19, 55, 49, 31], through post-processing the decisions [20], through adversarial learning [57, ”
Noise-tolerant fair classification (2019, background): “Recently, much progress has been made in this subject, both on devising sensible measures of fairness (Calders et al., 2009; Dwork et al., 2011; Feldman, 2015; Kim et al., 2018; Hardt et al., 2016; Zafar et al., 2017b,a; Kusner et al., 2017; Speicher et al., 2018; Zhang & Bareinboim, 2018; Heidari e”
Fairness in Machine Learning: A Survey (2020, background): “Computing by hand can introduce new biases without training [286], as fairness is typically not monotonic, thus assigning a threshold value may be quite arbitrary [270].”
Machine Translation into Low-resource Language Varieties (2021, methodology): “The generalized entropy index for a population of n individuals receiving beneﬁts b 1 , b 2 , . . . , b n with mean beneﬁt µ is Using α = 2 following Speicher et al. (2018), the generalized entropy index corresponds to half the squared coefﬁcient of variation.”
Bias Mitigation Post-processing for Individual and Group Fairness (2018, background): “Uniﬁed metrics for both group and individual fairness have recently been proposed [11] based on inequality indices [12].”
You Shouldn't Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods (2020, background): “• Theil Index (TI): between-group unfairness based on generalized entropy indices (Speicher et al. 2018).”
Fairness risk measures (2019, background): “Recently, several works [Zafar et al., 2017b, Dwork et al., 2018, Hashimoto et al., 2018, Alabi et al., 2018, Speicher et al., 2018, Donini et al., 2018, Heidari et al., 2019] have abstracted earlier deﬁnitions of fairness by framing the problem in terms of subgroup losses .”
Bayesian Modeling of Intersectional Fairness: The Variance of Bias (2018, background): “Fairness measurement is crucial when engineering AI systems for deployment [26].”
Fairness in Machine Learning (2020, methodology): “Some methods transform the constrained optimization problem via the method of Lagrange multipliers [3, 15, 34, 37, 38, 59, 97, 135, 183, 185] or add penalties to the objective [5, 14, 22, 44, 46, 56, 58, 62, 73, 74, 75, 79, 82, 87, 88, 89, 93, 94, 95, 98, 104, 115, 119, 123, 133, 134, 135, 138, 139,”