Rule Protection for Indirect Discrimination Prevention in Data Mining
By Sara Hajian, Josep Domingo-Ferrer, Antoni Martínez-Ballesté. 2011
75 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
- Aaron Roth
- Silvia Chiappa
- Luca Oneto
- Michael Kearns
- Bettina Berendt
- Sören Preibusch
- Matthew Joseph
- Jamie H. Morgenstern
In Safety Research
- Luca Oneto
- Silvia Chiappa
- Krishna P. Gummadi
- Aaron Roth
- Muhammad Bilal Zafar
- Isabel Valera
- Bettina Berendt
- Sören Preibusch
Citations in the corpus
- AN APPROACH FOR DISCRIMINATION PREVENTION IN DATA MINING (2014, background): “Martinez-Balleste[6] introduced an anti-discrimination in the context of cyber security.”
- Exploring Discrimination: A User-centric Evaluation of Discrimination-Aware Data Mining (2012, methodology): “Prevention is realised by a number of pre-processing and in-processing methods for DADM, and identification/filtering by a number of post-processing methods, e.g., [5-10].”
- Fair Learning in Markovian Environments (2016, background): “The first relaxation, which we call approximate-choice fairness, requires that an algorithm never chooses a worse action with probability substantially higher than better actions.”
- Fairness in Machine Learning (2020, methodology): “Pre-Processing methods consist in transforming the training data to remove undesired biases [16, 21, 24, 28, 47, 51, 52, 53, 61, 64, 65, 66, 67, 86, 90, 91, 92, 112, 114, 116, 118, 121, 122, 127, 126, 164, 174, 188, 190, 191, 193].”
- A Methodology for Direct and Indirect Discrimination Prevention in Data Mining (2013, result): “In [6], we introduced the use of rule protection in a different way for indirect discrimination prevention and we gave some preliminary experimental results.”
- The Bouncer Problem: Challenges to Remote Explainability (2019, methodology): “As the features that are considered discriminating are often precise [11,14], the test queries for fairness assessment can be targeted and some notions of efficiency in terms of the amount of requests can be derived.”
- Fairness Constraints: Mechanisms for Fair Classification (2015, methodology): “s have typically adopted one of the two following strategies. The first strategy consists of pre-processing (or massaging) the training data to limit discrimination (Kamiran & Calders, 2009; 2010; Hajian et al., 2011; Hajian & Domingo-Ferrer, 2012; Dwork et al., 2012; Zemel et al., 2013). Thi”