The paper tackles fair classification with multiple sensitive features.
problem Existing fair classification methods often consider a single sensitive feature, but in practice, individuals are defined by multiple sensitive features.
method Characterizes Bayes-optimal fair classifiers for multiple sensitive features under various fairness measures, proposing in-processing and post-processing algorithms.
result Bayes-optimal fair classifiers for multiple sensitive features are instance-dependent thresholding rules that rely on a weighted sum of group membership probabilities.
Most work in algorithmic fairness to date has focused on discrete outcomes, such as deciding whether to grant someone a loan or not. In these classification settings, group fairness criteria such as independence, separation and sufficiency can be measured directly by comparing rates of outcomes between subpopulations. …
The paper explores the tradeoffs between fairness measures in machine learning.
problem The challenge of achieving all three fairness notions simultaneously in machine learning models.
method The approach uses partial information decomposition (PID) to analyze the relationships between fairness measures.
result Identifies the regions where fairness measures overlap and disagree, revealing potential tradeoffs.
The paper explores intersectional fairness in machine learning, proving bounds on it.
problem Intersectional fairness in machine learning, especially when multiple protected attributes are involved.
method Statistical analysis and bounds on intersectional fairness, leveraging marginal fairness.
result Theoretical bounds on intersectional fairness can be computed from marginal fairness and other statistical quantities.
There has been much discussion recently about how fairness should be measured or enforced in classification. Individual Fairness [Dwork, Hardt, Pitassi, Reingold, Zemel, 2012], which requires that similar individuals be treated similarly, is a highly appealing definition as it gives strong guarantees on treatment of in…
The paper explores fairness in credit scoring using machine learning.
problem The lack of research on fair machine learning in credit scoring.
method Revisits statistical fairness criteria, catalogs algorithmic options, and empirically compares fairness processors.
result Multiple fairness criteria can be approximately satisfied at once, and fair processors deliver a good balance between profit and fairness.
In this paper we develop a novel methodology for estimation of risk capital allocation. The methodology is rooted in the theory of risk measures. We work within a general, but tractable class of law-invariant coherent risk measures, with a particular focus on expected shortfall. We introduce the concept of fair capital…
New causal approach resolves fairness and accuracy trade-offs.
problem Fairness and predictive performance are often at odds.
method Causal pre-processing methods to approximate the FiND world.
result Pre-processing resolves both fairness and accuracy trade-offs.
Standardized fairness measures for continuous risk scores using Wasserstein distance.
problem Quantifying and interpreting group disparities in continuous risk scores.
method Proposes standardized fairness measures based on Wasserstein distance for continuous scores.
result Proposed measures outperform ROC-based fairness measures by being more explicit and quantifying significant biases.
The paper explores the tradeoff between fairness and accuracy in regression models.
problem Characterizing the tradeoff between fairness and accuracy in regression models.
method Provided a lower bound on the error of any fair regressor and extended the result to joint error using Wasserstein distance.
result Lower bounds on the error of fair regressors and their connection to Wasserstein distance.
Algorithmic fairness involves expressing notions such as equity, or reasonable treatment, as quantifiable measures that a machine learning algorithm can optimise. Most work in the literature to date has focused on classification problems where the prediction is categorical, such as accepting or rejecting a loan applica…
Unified framework improves fair classification by selecting representative data points.
problem Improving fair classification outcomes in the presence of unintentional biases.
method Develops a unified framework to jointly optimize accuracy and fairness, recasting as mixed-integer convex programs.
result The framework can be used to enhance classification fairness by selecting more representative data points.
New dataset for evaluating speech recognition fairness across demographics.
problem Lack of fairness metrics in speech recognition datasets.
method Developed Fair-Speech dataset with diverse demographic information.
result Helps evaluate ASR models for fairness across demographics.
Paper tackles fair low-rank approximation and column subset selection.
problem Minimize loss over sub-populations in machine learning.
method Developed algorithms for fair low-rank approximation and fair column subset selection.
result Achieved polynomial time algorithms for fair low-rank approximation.
New fairness measures account for prediction uncertainties to detect bias.
problem Fairness of ML models is not well-defined and measures are limited.
method Introduce new fairness measures based on aleatoric and epistemic uncertainties.
result Uncertainty-based measures reveal bias not captured by existing measures.
Enhances fairness in multi-output models using optimal transport.
problem Improving fairness in multi-output models like multi-task/multi-class classification and representation learning.
method Post-processing method using optimal transport mappings to move model outputs towards empirical Wasserstein barycenter.
result Demonstrates effectiveness of the proposed approach on multi-task/multi-class classification and representation learning tasks.
New fairness concept extends minimax fairness to lexicographic fairness.
problem Fairness in supervised learning, especially lexicographic fairness.
method Introduced approximate lexifairness, derived algorithms for finding solutions, and proved generalization bounds.
result Proved that approximate lexifairness on training data implies approximate lexifairness on true distribution.
The development of fair machine learning models that effectively avert bias and discrimination is an important problem that has garnered attention in recent years. The necessity of encoding complex relational dependencies among the features and variables for competent predictions require the development of fair, yet ex…
A recent trend of fair machine learning is to define fairness as causality-based notions which concern the causal connection between protected attributes and decisions. However, one common challenge of all causality-based fairness notions is identifiability, i.e., whether they can be uniquely measured from observationa…
Bayesian data selection framework ensures fairness in machine learning models.
problem High computational costs and limited scalability of fairness-aware methods.
method Bayesian data selection framework using generalized discrepancy measures.
result Consistently outperforms existing methods in fairness and accuracy.
This paper introduces individual fairness in clustering using f-divergence.
problem Ensuring fair clustering by treating similar individuals similarly.
method Uses f-divergence to measure statistical similarity and assigns individuals to probability distributions over cluster centers. result Provides an algorithm with provable approximation guarantee for clustering with individual fairness constraints.
A distinction has been drawn in fair machine learning research between `group' and `individual' fairness measures. Many technical research papers assume that both are important, but conflicting, and propose ways to minimise the trade-offs between these measures. This paper argues that this apparent conflict is based on…
Study examines fairness in machine learning for credit scoring.
problem Bias in machine learning models for credit scoring.
method Comprehensive experimental study of fairness-aware machine learning models.
result Fairness-aware models improve fairness while maintaining accuracy.
Develops methods for fair classification under linear disparity constraints.
problem Disparate impacts of machine learning algorithms on protected groups.
method Bayes-optimal fair classification methods via pre-, in-, and post-processing.
result Explicit forms of Bayes-optimal fair classifiers under linear disparity measures.
In this paper, we study correlation clustering under fairness constraints. Fair variants of k-median and k-center clustering have been studied recently, and approximation algorithms using a notion called fairlet decomposition have been proposed. We obtain approximation algorithms for fair correlation clustering und…
Paper addresses fairness issues in error-prone outcomes.
problem Fairness in error-prone outcomes.
method Combining fair ML methods and measurement models.
result Using a latent variable model removes detected unfairness.
New method mitigates bias without sensitive data using causal graph and variational autoencoder.
problem Lack of fairness strategies when sensitive attributes are not collected.
method SRCVAE framework based on causal graph for inferring a proxy sensitive attribute.
result Significant improvements in fairness metrics over existing methods.
A new framework improves fairness in clustering and Wasserstein Barycenter problems.
problem Fair clustering in datasets with multiple groups.
method Relax and Merge framework for (1+4ρ+O(ε))-approximate solutions. result Improved approximation guarantees for fairness constraints.
Study develops a new method for creating fair models.
problem Ensuring equal outcomes for different protected groups.
method Introduces a new group-fair constraint based on transport maps.
result Develops a novel algorithm FTM for training group-fair models.
In this paper, we study counterfactual fairness in text classification, which asks the question: How would the prediction change if the sensitive attribute referenced in the example were different? Toxicity classifiers demonstrate a counterfactual fairness issue by predicting that "Some people are gay" is toxic while "…
Fairness measures fail in predictive settings that intentionally shift outcomes.
problem Fairness measures fail in performative prediction settings.
method Formalized concept shift and counterfactual outcomes.
result Predictors that are fair during training become unfair during deployment.
A new fairness metric for decision-making algorithms, conditioning on known fair variables.
problem Fairness issues in decision-making systems.
method Conditional fairness metric, Derivable Conditional Fairness Regularizer (DCFR), adversarial representation.
result Traditional fairness notations are special cases of the new conditional fairness notation.
FCA improves fair clustering by optimizing utility and fairness.
problem Balancing fairness and utility in clustering.
method FCA alternates between aligning data and optimizing cluster centers in an aligned space.
result FCA achieves a superior trade-off between fairness and utility.
Formulates LGFO to measure fair ML systems using legal signals.
problem Formally incompatible measures of unfairness in ML systems.
method Uses legal signals to measure social cost of unfairness.
result LGFO aligns with societal view of unfairness.
Proposes MFSWB for marginal fairness in SWB, improving efficiency and performance.
problem Achieving marginal fairness in SWB averaging.
method Defining MFSWB as a constrained SWB problem, proposing two surrogate problems and a new slicing distribution.
result Surrogate MFSWB problems effectively minimize distances to marginals and encourage marginal fairness.
The paper proposes a happiness-based fairness framework using linear programming.
problem Fairness in decision-making outcomes.
method Linear programming to compute optimal, fair post-processing strategies.
result Unified and extended fairness definitions with practical strengths across diverse scenarios.
New fairness criterion for risk-sensitive decisions in regulated industries.
problem Ensuring equitable outcomes in risk-sensitive decision-making.
method Marginal fairness for generalized distortion risk measures, two-step decision-making process.
result Ensures fairness in decision-making under risk measures, regardless of protected attributes.
This paper benchmarks algorithms for training fair DNNs, addressing real-world fairness constraints.
problem Training deep neural networks with fairness constraints.
method Benchmarking stochastic approximation algorithms for fairness-constrained DNN training.
result Demonstrates the use of a new benchmark for comparing fairness-improving algorithms.
We study an online learning problem subject to the constraint of individual fairness, which requires that similar individuals are treated similarly. Unlike prior work on individual fairness, we do not assume the similarity measure among individuals is known, nor do we assume that such measure takes a certain parametric…
The paper shows how to use proxy attributes for fairness in machine learning models with missing sensitive group data.
problem Measuring and enforcing fairness in machine learning models with incomplete sensitive group data.
method Using proxy-sensitive attributes to derive upper bounds on multiaccuracy and multicalibration violations and adjust models to satisfy these fairness notions.
result Provable upper bounds on multiaccuracy and multicalibration violations can be derived using proxy-sensitive attributes in the absence of sensitive group data.
Proposes measuring fairness through multiple stakeholder-curated stress tests.
problem Limited power of rigid fairness metrics and lack of stakeholder involvement in fairness discussions.
method Shift focus from fairness metrics to stress tests curated by stakeholders.
result Machine's performance under multiple stress tests reflects fairness.
Efficiently approximates fairness-accuracy trade-offs for diverse datasets.
problem Inherent trade-off between fairness and accuracy in machine learning models.
method You-Only-Train-Once (YOTO) framework for computationally efficient approximation.
result Robust methodology for auditing model fairness with statistical guarantees.
A new method learns fair classifiers without sacrificing accuracy.
problem Designing fair classifiers that do not discriminate based on sensitive attributes.
method A model-agnostic multi-objective architecture using a differentiable relaxation of fairness notions.
result Our method achieves lower loss of accuracy compared to current debiasing algorithms.
We study the question of fair clustering under the {\em disparate impact} doctrine, where each protected class must have approximately equal representation in every cluster. We formulate the fair clustering problem under both the k-center and the k-median objectives, and show that even with two protected classes th…
The paper connects counterfactual fairness to robust prediction and group fairness using causal context.
problem The challenge of ensuring fairness in AI systems when counterfactuals cannot be directly observed.
method Using causal context to bridge counterfactual fairness, robust prediction, and group fairness.
result Counterfactual fairness is equivalent to group fairness metrics in specific contexts.
We give a local search based algorithm for k-median and k-means (and more generally for any k-clustering with ℓp norm cost function) from the perspective of individual fairness. More precisely, for a point x in a point set P of size n, let r(x) be the minimum radius such that the ball of radius $r(x…
We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conceptual mapping, many existing definition of algorithmic fairness, such as predictive value parity and…
One often finds in the literature connections between measures of fairness and measures of feature importance employed to interpret trained classifiers. However, there seems to be no study that compares fairness measures and feature importance measures. In this paper we propose ways to evaluate and compare such measure…