Three naive Bayes approaches for discrimination-free classification

@article{Calders2010ThreeNB,
  title={Three naive Bayes approaches for discrimination-free classification},
  author={Toon Calders and Sicco Verwer},
  journal={Data Mining and Knowledge Discovery},
  year={2010},
  volume={21},
  pages={277-292}
}
  • T. Calders, S. Verwer
  • Published 1 September 2010
  • Computer Science
  • Data Mining and Knowledge Discovery
In this paper, we investigate how to modify the naive Bayes classifier in order to perform classification that is restricted to be independent with respect to a given sensitive attribute. Such independency restrictions occur naturally when the decision process leading to the labels in the data-set was biased; e.g., due to gender or racial discrimination. This setting is motivated by many cases in which there exist laws that disallow a decision that is partly based on discrimination. Naive… 
Introducing Positive Discrimination in Predictive Models
  • S. Verwer, T. Calders
  • History, Computer Science
    Discrimination and Privacy in the Information Society
  • 2013
TLDR
In this chapter, three solutions for the discrimination-aware classification problem that are based upon Bayesian classifiers are given that can be seen as ways to introduce positive discrimination.
Techniques for Discrimination-Free Predictive Models
TLDR
This chapter studies a case of income prediction, where the available historical data exhibits a wage gap between the genders, and the discrimination-aware techniques succeed in significantly reducing gender discrimination without impairing too much the accuracy.
Handling Conditional Discrimination
TLDR
This work develops local techniques for handling conditional discrimination when one of the attributes is considered to be explanatory, and demonstrates that the new local techniques remove exactly the bad discrimination, allowing differences in decisions as long as they are explainable.
Discrimination Aware Decision Tree Learning
TLDR
Experimental evaluation shows that the proposed approach advances the state-of-the-art in the sense that the learned decision trees have a lower discrimination than models provided by previous methods, with little loss in accuracy.
Decision Theory for Discrimination-Aware Classification
TLDR
The first and second solutions exploit the reject option of probabilistic classifier(s) and the disagreement region of general classifier ensembles to reduce discrimination and relate both solutions with decision theory for better understanding of the process.
Data preprocessing techniques for classification without discrimination
TLDR
This paper surveys and extends 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 and presents the results of experiments on real-life data.
Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patterns
TLDR
This paper proposes an algorithm to discover and mine for discrimination patterns in a naive Bayes classifier, and shows how to learn maximum likelihood parameters subject to these fairness constraints.
Exploiting reject option in classification for social discrimination control
TLDR
This paper utilizes reject option in classification, a general decision theoretic framework for handling instances whose labels are uncertain, for modeling and controlling discriminatory decisions, and presents three different solutions for discrimination-aware classification that are effective at removing illegal discrimination from the predictions.
Quantifying explainable discrimination and removing illegal discrimination in automated decision making
TLDR
The refined notion of conditional non-discrimination in classifier design is introduced and it is shown that some of the differences in decisions across the sensitive groups can be explainable and are hence tolerable.
Combating discrimination using Bayesian networks
TLDR
A discrimination discovery method based on modeling the probability distribution of a class using Bayesian networks and a classification method that corrects for the discovered discrimination without using protected attributes in the decision process are proposed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 15 REFERENCES
Classifying without discriminating
  • F. Kamiran, T. Calders
  • Computer Science
    2009 2nd International Conference on Computer, Control and Communication
  • 2009
TLDR
This paper proposes a new classification scheme for learning unbiased models on biased training data based on massaging the dataset by making the least intrusive modifications which lead to an unbiased dataset and learns a non-discriminating classifier.
Discrimination-aware data mining
TLDR
This approach leads to a precise formulation of the redlining problem along with a formal result relating discriminatory rules with apparently safe ones by means of background knowledge, and an empirical assessment of the results on the German credit dataset.
The Foundations of Cost-Sensitive Learning
TLDR
It is argued that changing the balance of negative and positive training examples has little effect on the classifiers produced by standard Bayesian and decision tree learning methods, and the recommended way of applying one of these methods is to learn a classifier from the training set and then to compute optimal decisions explicitly using the probability estimates given by the classifier.
Data mining for discrimination discovery
TLDR
This article formalizes the processes of direct and indirect discrimination discovery by modelling protected-by-law groups and contexts where discrimination occurs in a classification rule based syntax and proposes two inference models and provides automatic procedures for their implementation.
Classification with No Discrimination by Preferential Sampling
The concept of classification without discrimination is a new area of research. (Kamiran & Calders, ) introduced the idea of Classification with No Discrimination (CND)and proposed a solution based
Measuring Discrimination in Socially-Sensitive Decision Records
TLDR
This work tackles the problem of determining, given a dataset of historical decision records, a precise measure of the degree of discrimination suffered by a given group in a given context with respect to the decision, and introduces a collection of quantitative measures of discrimination.
Learning decision trees for loss minimization in multi-class problems
TLDR
This work studies methods for modifying C4.5 to incorporate arbitrary loss matrices and tests several methods: a wrapper method and some simple heuristics, and shows that this measure can predict when more e cient methods will be applied and when the wrapper method must be applied.
Nearest Neighbour Classification with Monotonicity Constraints
TLDR
A modified nearest neighbour algorithm for the construction of monotone classifiers from data is proposed that often outperforms standard kNN in problems where the monotonicity constraints are applicable.
Building Classifiers with Independency Constraints
TLDR
This paper studies the classification with independency constraints problem: find an accurate model for which the predictions are independent from a given binary attribute and proposes two solutions and presents an empirical validation.
Statistical Model for Rough Set Approach to Multicriteria Classification
TLDR
A new approach to variable consistency that is based on maximum likelihood estimation is introduced and the equivalence of the variable consistency rough sets to the specific risk-minimizing decision rule in statistical decision theory is shown.
...
1
2
...