Measuring discrimination in algorithmic decision making

By Indrė Žliobaitė. 2017

278 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety Research

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

Citations in the corpus

On formalizing fairness in prediction with machine learning (2017, background): “For how the fairness (or alternatively discrimination) is measured , we point the readers to ˇZliobait˙e [82].”
Algorithmic Decision Making and the Cost of Fairness (2017, background): “Romei and Ruggieri [36] and Zliobaite [42] survey various measures of fairness in decision making.”
A comparative study of fairness-enhancing interventions in machine learning (2018, background): “We find surprising variability in fairness measures arising from variations in training-test splits; this appears to not have been previously mentioned in the literature.”
A Nutritional Label for Rankings (2018, background): “view of the Fairness widget in our example presents the output of three fairness measures: FA*IR [14], proportion [15], and our own pairwise measure.”
Algorithmic Fairness (2020, background): “This measures the difference between the means of the predictions across groups [152].”
Economics, Fairness and Algorithmic Bias (2020, unknown): “Some papers go beyond legal requirements and examine other plausible definitions of fairness (Romei and Ruggieri, 2014; Žliobaitė, 2017).”
Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees (2018, background): “vey [63] for other relaxed fairness metrics, e.”
Designing Fair Ranking Schemes (2017, background): “Numerous fairness definitions have been considered in the literature [14, 33].”
A survey on datasets for fairness‐aware machine learning (2021, background): “Only in the computer science research area, more than 20 measures of fairness have been introduced thus far (ˇZliobait˙e, 2017; Verma & Rubin, 2018).”
Bias in data‐driven artificial intelligence systems—An introductory survey (2020, background): “More than 20 different definitions of fairness have appeared thus far in the computer science literature (Verma & Rubin, 2018; Zliobaite, 2017); and some of these definitions and others were proposed and investigated in work on formalizing fairness from other disciplines, such as education, over…”
The relationship between trust in AI and trustworthy machine learning technologies (2019, background): “• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies (2023, background): “Another difference is that bias can be either positive or negative, whereas fairness is only concerned with negative bias or discrimination [36].”
Bias Mitigation Post-processing for Individual and Group Fairness (2018, background): “Checking for group fairness is a fairly straightforward computation of statistical metrics [8], but checking for individual fairness is more computationally involved when there are many protected attributes with many values and scoring samples using a model is expensive [9, 10].”