A survey on datasets for fairness‐aware machine learning

Published in

(2021)

External Links:

Generate Graph DownloadPDF

TL;DR

This paper overviews real‐world datasets used for fairness‐aware ML by identifying relationships between the different attributes, particularly with respect to protected attributes and class attribute, using a Bayesian network.

Abstract

As decision‐making increasingly relies on machine learning (ML) and (big) data, the issue of fairness in data‐driven artificial intelligence systems is receiving increasing attention from both research and industry. A large variety of fairness‐aware ML solutions have been proposed which involve fairness‐related interventions in the data, learning algorithms, and/or model outputs. However, a vital part of proposing new approaches is evaluating them empirically on benchmark datasets that represent realistic and diverse settings. Therefore, in this paper, we overview real‐world datasets used for fairness‐aware ML. We focus on tabular data as the most common data representation for fairness‐aware ML. We start our analysis by identifying relationships between the different attributes, particularly with respect to protected attributes and class attribute, using a Bayesian network. For a deeper understanding of bias in the datasets, we investigate interesting relationships using exploratory analysis.

Authors

Tai Le Quy

1 papers

Arjun Roy

1 papers

Vasileios Iosifidis

1 papers

References161 items

Longitudinal Fairness with Censorship

Fair Decision-making Under Uncertainty

FARF: A Fair and Adaptive Random Forests Classifier

Retiring Adult: New Datasets for Fair Machine Learning

Minimax Group Fairness: Algorithms and Experiments

A survey on datasets for fairness‐aware machine learning

Published in

(2021)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Tai Le Quy

1 papers

Arjun Roy

1 papers

Vasileios Iosifidis

1 papers

References161 items

Longitudinal Fairness with Censorship

Fair Decision-making Under Uncertainty

FARF: A Fair and Adaptive Random Forests Classifier

Retiring Adult: New Datasets for Fair Machine Learning

Minimax Group Fairness: Algorithms and Experiments

Eirini Ntoutsi

1 papers

Variational Fair Clustering

Effect of Information Presentation on Fairness Perceptions of Machine Learning Predictors

Fair-Capacitated Clustering

Fairness in rankings and recommendations: an overview

Consequence-aware Sequential Counterfactual Generation

Learning to Generate Fair Clusters from Demonstrations

Making Artificial Intelligence Transparent: Fairness and the Problem of Proxy Variables

Data and its (dis)contents: A survey of dataset development and use in machine learning research

The Crucial Role of Sensitive Attributes in Fair Classification

How Do Fair Decisions Fare in Long-term Qualification?

Making Fair ML Software using Trustworthy Explanation

Minimax Pareto Fairness: A Multi Objective Perspective

How fair can we go in machine learning? Assessing the boundaries of accuracy and fairness

Fair Clustering via Equitable Group Representations

Probabilistic Fair Clustering

Algorithmic Decision Making with Conditional Fairness

Fairness without Demographics through Adversarially Reweighted Learning

Fair Outlier Detection

FairNN- Conjoint Learning of Fair Representations for Fair Decisions

Fairway: a way to build fair ML software

Fair regression via plug-in estimator and recalibration with statistical guarantees

Learning Certified Individually Fair Representations

(Individual) Fairness for k-Clustering

Bias in data‐driven artificial intelligence systems—An introductory survey

Fairness is not static: deeper understanding of long term fairness via simulation studies

Algorithmic Fairness

FairPrep: Promoting Data to a First-Class Citizen in Studies on Fairness-Enhancing Interventions

Fair Adversarial Gradient Tree Boosting

On Fairness-Aware Learning for Non-discriminative Decision-Making

Fairness in Clustering with Multiple Sensitive Attributes

AdaFair: Cumulative Fairness Adaptive Boosting

Fairness warnings and fair-MAML: learning fairly with minimal data

A Survey on Bias and Fairness in Machine Learning

Fairness in Deep Learning: A Computational Perspective

FairSight: Visual Analytics for Fairness in Decision Making

FAHT: An Adaptive Fairness-aware Decision Tree Classifier

Operationalizing Individual Fairness with Pairwise Fair Representations

Time-to-Event Prediction with Neural Networks and Cox Regression

Coresets for Clustering with Fairness Constraints

Pairwise Fairness for Ranking and Regression

Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patterns

Subgroup identification for precision medicine: A comparative review of 13 methods

Average Individual Fairness: Algorithms, Generalization and Experiments

Evaluating the Fairness of Predictive Student Models Through Slicing Analysis

Scalable Fair Clustering

A Framework for Benchmarking Discrimination-Aware Models in Machine Learning

Algorithms for Fairness in Sequential Decision Making

Fair Algorithms for Clustering

Taking Advantage of Multitask Learning for Fair Classification

Hunting for Discriminatory Proxies in Linear Regression Models

Fairness through Causal Awareness: Learning Causal Latent-Variable Models for Biased Data

An Empirical Study of Rich Subgroup Fairness for Machine Learning

Multicalibration: Calibration for the (Computationally-Identifiable) Masses

Preventing Disparate Treatment in Sequential Decision Making

Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making

Fairness Definitions Explained

Beyond Distributive Fairness in Algorithmic Decision Making: Feature Selection for Procedurally Fair Learning

Adaptive Sensitive Reweighting to Mitigate Bias in Fairness-aware Classification

Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods

Delayed Impact of Fair Machine Learning

A Reductions Approach to Fair Classification

Fair Clustering Through Fairlets

A comparative study of fairness-enhancing interventions in machine learning

Mitigating Unwanted Biases with Adversarial Learning

Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification

Recycling Privileged Learning and Distribution Matching for Fairness

When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness

Open University Learning Analytics dataset

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

Proxy Non-Discrimination in Data-Driven Systems

Penalizing Unfairness in Binary Classification

A Convex Framework for Fair Regression

Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs

Measuring discrimination in algorithmic decision making

Counterfactual Fairness

Algorithmic Decision Making and the Cost of Fairness

Using the machine learning approach to predict patient survival from high-dimensional survival data

Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment

Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments

Equality of Opportunity in Supervised Learning

Big Data and Social Science: A Practical Guide to Methods and Tools

The Problem of Infra-Marginality in Outcome Tests for Discrimination

A Confidence-Based Approach for Balancing Fairness and Accuracy

Learning Discrete Bayesian Networks from Continuous Data

Fairness Constraints: Mechanisms for Fair Classification

On the relation between accuracy and fairness in binary classification

Ricci v. DeStefano

Certifying and Removing Disparate Impact

Thinking fast and slow.

Automated Experiments on Ad Privacy Settings

A data-driven approach to predict the success of bank telemarketing

Impact of HbA1c Measurement on Hospital Readmission Rates: Analysis of 70,000 Clinical Database Patient Records

Combating discrimination using Bayesian networks

Controlling Attribute Effect in Linear Regression

100

Discrimination aware classification for imbalanced datasets

101

A Methodology for Direct and Indirect Discrimination Prevention in Data Mining

102

Learning Fair Representations

103

Quantifying explainable discrimination and removing illegal discrimination in automated decision making

104

A multidisciplinary survey on discrimination analysis

105

Fairness-Aware Classifier with Prejudice Remover Regularizer

106

The RcmdrPlugin.survival Package: Extending the R Commander Interface to Survival Analysis

107

Application of Machine Learning Algorithms to an online Recruitment System

108

Handling Conditional Discrimination

109

Data preprocessing techniques for classification without discrimination

110

k-NN as an implementation of situation testing for discrimination discovery and prevention

111

Fairness through awareness

112

Discrimination Aware Decision Tree Learning

113

Probabilistic Modeling in Bioinformatics and Medical Informatics

114

Three naive Bayes approaches for discrimination-free classification

115

Data mining for discrimination discovery

116

Building Classifiers with Independency Constraints

117

Classifying without discriminating

118

The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients

119

Discrimination-aware data mining

120

Using data mining to predict secondary school student performance

121

Multi–objective Evolutionary Algorithms for the Risk–return Trade–off in Bank Loan Management

122

Applied Logistic Regression

123

An expert system approach to graduate school admission decisions and academic performance prediction

124

Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid

125

Age Discrimination and the Disparate Impact Doctrine

126

The Regression Analysis of Binary Sequences

127

The Supreme Court of the United States

128

An Overview of Fairness in Clustering

129

A Systematic Review of Fairness in Artificial Intelligence Algorithms

130

Integrated Public Use Microdata Series

131

Harmonic-Mean Cox Models: A Ruler for Equal Attention to Risk

132

Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics

133

FABBOO - Online Fairness-Aware Learning Under Class Imbalance

134

Towards Formal Fairness in Machine Learning

135

Fairness with Overlapping Groups; a Probabilistic Perspective

136

Fairness in Learning Analytics: Student At-risk Prediction in Virtual Learning Environments

137

FEAT: A Fairness-Enhancing and Concept-Adapting Decision Tree Classifier

138

Predictive Algorithms in Learning Analytics and their Fairness

139

Fairness Constraints: A Flexible Approach for Fair Classification

140

Evaluation and experimental design in data mining and machine learning: Motivation and summary of EDML 2019

141

Dealing with Bias via Data Augmentation in Supervised Learning Scenarios

142

Note that the majority of fairness-aware ML methods can handle only single protected attribures. The problem of multifairness has only recently been addressed

143

Optimized Pre-Processing for Discrimination Prevention

145

Fairer and more accurate

146

Learning fair classifiers : A regularization approach

148

Computational Fairness: Preventing Machine-Learned Discrimination

149

Fair Boosting : a Case Study

150

Probing the dark side of google’s ad-targeting system

151

Introduction to Bayesian Networks

152

Classification with no discrimination by preferential sampling

153

Kamiran & Calders

154

Measuring Discrimination in Socially-Sensitive Decision Records

155

Innovations in Bayesian Networks

156

Uci machine learning repository

157

SMOTE: Synthetic Minority Over-sampling Technique

158

The 2001 census in the netherlands

159

LSAC National Longitudinal Bar Passage Study. LSAC Research Report Series.

160

The SUPPORT prognostic model. Objective estimates of survival for seriously ill hospitalized adults. Study to understand prognoses and preferences for outcomes and risks of treatments.

161

Chzhen et al., 2020; Kearns et al., 2019; Kusner et al., 2017; Russell et al., 2017; Lahoti et al., 2020; Bechavod & Ligett, 2017; Berk et al., 2017; Yang et al., 2020; Ruoss et al., 2020