Optimized Pre-Processing for Discrimination Prevention

By Flávio du Pin Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, Kush R. Varshney. 2017

843 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

Fair Resource Allocation in Federated Learning (2019, methodology): “Two common approaches are to preprocess the data to remove information about the protected attribute, or to post-process the model by adjusting the prediction threshold after classifiers are trained (Feldman, 2015; Hardt et al., 2016; Calmon et al., 2017).”
Learning Adversarially Fair and Transferable Representations (2018, background): “Calmon et al. (2017) and Hajian et al. (2015) explored fair machine learning by pre-and post-processing training datasets.”
Wasserstein Fair Classification (2019, methodology): “rst approach consists in pre-processing the data to remove bias, or in extracting representations 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”
Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure (2019, methodology): “Generating debiased data: Recent approaches have utilized generative models (Sattigeri et al. 2018) and data transformations (Calmon et al. 2017) to generate training data that is more ‘fair’ than the original dataset.”
The Price of Fair PCA: One Extra Dimension (2018, background): “The ﬁrst piece is a broad line of work [Zemel et al., 2013; Beutel et al., 2017; Calmon et al., 2017; Madras et al., 2018; Zhang et al., 2018] that aims to design representations which will be conditionally independent of the protected attribute, while retaining as much information as possible (and…”
Taking Advantage of Multitask Learning for Fair Classification (2018, background): “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, background): “Optimized preprocessing (Calmon et al., 2017) learns a probabilistic transformation that edits the features and labels in the data with group fairness, individual distortion, and data ﬁdelity constraints and objectives.”
Path-Specific Counterfactual Fairness (2018, methodology): “A more sophisticated approach is to pre-process the data or extract representations that do not contain information about the sensitive attribute (Zemel et al., 2013; Feldman et al., 2015; Edwards & Storkey, 2016; Louizos et al., 2016; Calmon et al., 2017).”
On the Fairness of Disentangled Representations (2019, background): “[12] introduces the idea of data pre-processing as a tool to control for downstream discrimination.”
Learning Fair Rule Lists (2019, background): “earning While many approaches have been proposed in the literature to enhance the fairness of machine learning methods, they can be categorized in three main families, namely preprocessing techniques [11, 23, 30, 63], algorithmic modificationtechniques [10, 31, 32, 62] and postprocessing techniques ”
Learning Optimized Risk Scores (2016, background): “Current approaches often aim to address a specific kind of constraints for generic models via pre- or post-processing (see e.g., Goh et al., 2016; Calmon et al., 2017).”
A Reductions Approach to Fair Classification (2018, methodology): “The second group of approaches eliminate the restriction to specific classifier families and treat the underlying classification method as a “black box,” while implementing a wrapper that either works by pre-processing the data or post-processing the classifier’s predictions (e.g., Kamiran & Calders”
A comparative study of fairness-enhancing interventions in machine learning (2018, methodology): “Additional preprocessing approaches include Calmon et al. (2017); Kamiran and Calders.”
Learning Controllable Fair Representations (2018, background): “Calmon et al. (2017) transform the dataset to prevent discrimination on specific classification tasks.”
Empirical Risk Minimization under Fairness Constraints (2018, methodology): “Finally, the third family of methods implements fairness by modifying the data representation and then employs standard machine learning methods: [31, 7, 32, 4, 33, 34] are examples of these methods but, again, no consistency property nor comparison with state-of-the-art proposal are provided.”
Algorithmic Fairness (2020, methodology): “More recent mechanisms suggest modifying feature representations, so that a subsequent classifier will be fairer [30, 54, 94, 122, 144].”
Fairness Constraints: A Flexible Approach for Fair Classification (2019, methodology): “(2015); Calmon et al. (2017). The goal is to pre-process the training data such that any classification algorithm trained on this data would generate unfairness-free outcomes. This strategy can be roughly divided into two different sub-categories. Below, we briefly discuss these subcategories: The f”
Fairness in Machine Learning (2020, methodology): “In many recent papers [1, 3, 6, 14, 15, 16, 24, 44, 46, 52, 69, 90, 91, 92, 96, 97, 128, 149, 153, 177, 183, 184, 186, 188] it has been shown how to enforce EFPRs/EFNRs during model training.”