Data preprocessing techniques for classification without discrimination

By Faisal Kamiran, Toon Calders. 2011

1,608 citations recorded by the source corpus.

Recently, the following Discrimination-Aware Classification Problem was introduced: Suppose we are given training data that exhibit unlawful discrimination; e.g., toward sensitive attributes such as gender or ethnicity. The task is to learn a classifier that optimizes accuracy, but does not have this discrimination in its predictions on test data. This problem is relevant in many settings, such as when the data are generated by a biased decision process or when the sensitive attribute serves as a proxy for unobserved features. In this paper, we concentrate on the case with only one binary sensitive attribute and a two-class classification problem. We first study the theoretically optimal trade-off between accuracy and non-discrimination for pure classifiers. Then, we look at algorithmic solutions that preprocess the data to remove discrimination before a classifier is learned. We survey and extend our existing data preprocessing techniques, being suppression of the sensitive attribute, massaging the dataset by changing class labels, and reweighing or resampling the data to remove discrimination without relabeling instances. These preprocessing techniques have been implemented in a modified version of Weka and we present the results of experiments on real-life data.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability

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, Robustness & Interpretability

Citations in the corpus

On The Impact of Machine Learning Randomness on Group Fairness (2023, methodology): “This variance persists even with state-of-the-art bias mitigation algorithms (Reweighing [30]; Equalized Odds Loss [22]; FairBatch [46]) (b) The overall performance (F1 score), however, has a significantly smaller range of variance.”
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “An example is Reweighing [395] , which mod-iﬁes the weights of the features in order to remove discrimination in sensitive attributes.”
A Survey on Bias and Fairness in Machine Learning (2019, background): “ring Simpson’s paradoxes in data. Algorithm Reference Pre-Processing In-Processing Post-Processing Community detection [85] ✓ Word embedding [22] ✓ Optimized pre-processing [26] ✓ Data pre-processing [63] ✓ Classification [130] ✓ Regression [13] ✓ Classification [65] ✓ Classification [127] ✓ Adversa”
Causal Modeling-Based Discrimination Discovery and Removal: Criteria, Bounds, and Algorithms (2019, methodology): “For example, [2], [6] proposed several methods for modifying data, includingMassaging, which changes the labels of some individuals in the dataset to remove discrimination, Reweighting, which assigns weights to individuals to balance the dataset, and Sampling, which changes the sample sizes of diffe”
Wasserstein Fair Classification (2019, background): “…that do not contain sensitive information during training (Beutel et al., 2017; Calders et al., 2009; Calmon et al., 2017; Edwards and Storkey, 2016; Feldman et al., 2015; Fish et al., 2015; Kamiran and Calders, 2009, 2012; Louizos et al., 2016; Zemel et al., 2013; ˇZliobaite et al., 2011).”
Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making (2019, methodology): “First, pre-processing approaches, which rely on modifying the data to eliminate or neutralize any preexisting bias and subsequently apply standard ML techniques (Kamiran and Calders 2012; 2009; Luong, Ruggieri, and Turini 2011).”
Stable and Fair Classification (2019, methodology): “Finally, a diﬀerent line of research pre-processes the training data with the goal of removing the bias for learning, e.g., [39, 51, 40, 76, 26, 44].”
The Price of Fair PCA: One Extra Dimension (2018, background): “…work has developed techniques to obfuscate a sensitive attribute directly [Pedreshi et al., 2008; Kamiran et al., 2010; Calders and Verwer, 2010; Kamiran and Calders, 2011; Luong et al., 2011; Kamiran et al., 2012; Kamishima et al., 2012; Hajian and Domingo-Ferrer, 2013; Feldman et al., 2015;…”
Taking Advantage of Multitask Learning for Fair Classification (2018, neutral): “This is in contrast to other approaches which impose the fairness constraint as a post-processing step [10 19 20 31] or by modifying the data representation before employing standard machine learning methods [1 12 22–24 39].”
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias (2018, methodology): “…is one such repository that provides a few fairness metrics, such as mean difference, as well as some bias mitigation algorithms, such as relabeling (Kamiran & Calders, 2012), additive counterfactually fair estimator (Kusner et al., 2017), and reject option classiﬁcation (Kamiran et al., 2012).”
Adaptive Sensitive Reweighting to Mitigate Bias in Fairness-aware Classification (2018, background): “Such approaches include massaging the dataset [3, 13, 16, 24–26] by changing class labels that are identified as mislabeled due to bias and reweighting (usually heuristically) training samples so that more importance is placed on sensitive ones [3, 11, 25].”
A Convex Framework for Fair Regression (2017, background): “As a result, research on fairness in machine learning and statistics has seen rapid growth in recent years [1, 5–7, 9–11, 13, 14, 18–21, 25, 27], and several mathematical formulations have been proposed as metrics of (un)fairness for a number of diﬀerent learning frameworks.”
Fairness in Criminal Justice Risk Assessments: The State of the Art (2017, background): “Instructive deﬁnitions can be found in computer science (Pedreschi, 2008; Kamishima et al., 2011; Dwork et al., 2012; Kamiran et al., 2012; Chouldechova, 2016; Friedler et al., 2016; Hardt et al., 2016; Joseph et al., 2016; Kleinberg et al., 2016; Calmon et al., 2017; Corbitt-Davies et al., 2017),…”