The Case for Process Fairness in Learning: Feature Selection for Fair Decision Making

By Nina Grgic-Hlaca, Muhammad Bilal Zafar, Krishna P. Gummadi, Adrian Weller. 2016

237 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

A Survey on Bias and Fairness in Machine Learning (2019, background): “d receive a similar outcome. Definition 5.(Fairness Through Unawareness). "An algorithm is fair as long as any protected attributes A are not explicitly used in the decision-making process" [53, 73]. Definition 6.(Treatment Equality). "Treatment equality is achieved when the ratio of ”
Counterfactual Fairness (2017, background): “These include fairness through unawareness [12], individual fairness [10, 16, 24, 38], demographic parity/disparate impact [36], and equality of opportunity [14, 37].”
FairSight: Visual Analytics for Fairness in Decision Making (2019, background): “It is also the case of the real-world practice that, according to [17], the data collecting and processing is the most preferable and time-consuming task.”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “If people have strong intuitions about the fairness of using particular features in a model (regardless of their weights), as has been observed in a previous study by Grgic et al [28], this may account for such consistency.”
A Systematic Study of Bias Amplification (2022, background): “These formulations include equalized odds and equalized opportunity [18], fairness through awareness [13] or unawareness [16, 26], treatment equality [2], and demographic parity [13, 26].”
Gender differences in beliefs about algorithmic fairness (2017, result): “Our finding is also consistent with the results in [7], which identifies evidence of gender differences in beliefs about which features are acceptable to use in criminal risk prediction, although they do not assess statistical significance because their sample is small.”
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).”
Counterfactual Fairness Is Basically Demographic Parity (2022, background): “This approach has been called “fairness through unawareness” (Grgic-Hlaca et al. 2016) and fails to make fair decisions because protected attributes are often redundantly encoded (Pedreshi, Ruggieri, and Turini 2008).”
Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction (2018, background): “ions around the above question for multiple reasons: First, people’s judgments about fairness of using features can be leveraged to learn fair algorithmic decision making, as shown in our recent work [28, 29]. Second, arXiv:1802.09548v1 [stat.ML] 26 Feb 2018 while the question, “is this feature fair”
Ethical Considerations in AI-Based Recruitment (2019, background): “Previous surveys [10, 13-18] and work in fairness in machine learning have not addressed the types of biases that past studies have shown occur in the recruitment process, such as confirmation bias (decisions made in the first few minutes of meeting a candidate) and expectation anchor bias (being in”
Bias and Debias in Recommender System: A Survey and Future Directions (2020, background): “There exist many diferent variations of fairness deinition, which can be roughly categorized into four types: 1) fairness through unawareness [58]; 2) individual fairness [49, 79, 112, 204]; 3) group fairness (e.”