Develops fair classifiers robust to training distribution perturbations.
problem Ensuring fairness in classifiers robust to training data perturbations.
method Formulates a min-max objective function to minimize distributionally robust training loss while maintaining fairness for perturbed distributions. Uses an iterative online learning algorithm to find a fair and robust classifier.
result Our classifier maintains fairness and accuracy for a wide range of perturbations compared to state-of-the-art fair classifiers.
Consider a binary decision making process where a single machine learning classifier replaces a multitude of humans. We raise questions about the resulting loss of diversity in the decision making process. We study the potential benefits of using random classifier ensembles instead of a single classifier in the context…
Fair Mixup improves fairness in classifiers by interpolating between groups.
problem Ensuring fairness in classifiers during training and evaluation.
method Fair Mixup uses interpolation of samples between groups to enforce fairness constraints.
result Fair Mixup ensures better generalization of fairness in various benchmarks.
PAC-Bayesian framework for fairness in stochastic and deterministic classifiers.
problem Theoretical guarantees on fairness for balancing predictive risk and fairness constraints.
method PAC-Bayesian framework for both stochastic and deterministic classifiers, covering a broad class of fairness measures.
result Derives generalization bounds for fairness, demonstrating tightness with empirical evaluation.
OTF uses optimal transport to measure classifier fairness.
problem Measuring and reducing unfairness in classifier predictions.
method Introduces Optimal Transport to Fairness (OTF) to quantify and reduce unfairness.
result OTF improves the balance between classifier performance and fairness.
Extracts fairness truth from classifiers using an oracle.
problem Fairness in classification algorithms without context.
method Uses fairness oracle to learn underlying fairness truth.
result Extracts metric fairness from classifiers.
Unified framework for Bayes-optimal classifiers under group fairness.
problem Mitigating disparate impacts from algorithmic predictions in high-stakes decision-making.
method Unified framework based on Neyman-Pearson argument for deriving Bayes-optimal classifiers under group fairness constraints.
result Proposes FairBayes method that directly controls disparity and achieves optimal fairness-accuracy tradeoff.
The paper explores the incompatibility between fair privacy, need-to-know, and fairness in classifier outputs.
problem The interaction between fair privacy, need-to-know, and fairness in classifier outputs.
method Formulated and explored the interaction between fair privacy, need-to-know, and fairness in classifier outputs.
result Optimal classifiers are generally incompatible with fair privacy and need-to-know.
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 "…
Develops a fair classifier for deep learning models.
problem Ensuring fairness in classification models across different sub-populations.
method Applies Rawlsian principles to minimize error rate on the worst-off sub-population.
result Introduces a practical method to adapt any black-box deep learning model to be fair.
Differentially private fair binary classification algorithm developed.
problem Balancing privacy and fairness in binary classification.
method Decoupling technique for fairness, refinement for differential privacy.
result Algorithm maintains fairness, privacy, and utility guarantees.
Proposes a method to learn fair classifiers without restrictive assumptions.
problem Fairness in machine learning decisions for individuals.
method Defines PIU and optimizes to control its upper bound.
result Guarantees fairness for each individual without restrictive assumptions.
Unified approach for fair classification with overlapping groups.
problem Ensuring fairness across multiple overlapping groups in prediction problems.
method Probabilistic population analysis leading to Bayes-optimal classifier, unifying existing methods.
result Outperforms baselines in fairness-performance tradeoff on real datasets.
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.
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.
New framework reduces strategic manipulation cost for minority groups in fair classification.
problem Strategic manipulation disparities in fair classification.
method Constrained optimization framework that constructs classifiers to reduce strategic manipulation cost for minority groups.
result Empirically, the approach reduces strategic manipulation cost for minority groups over multiple real-world datasets.
Paper characterizes fairness vs. accuracy tradeoff in classification.
problem Mitigating bias in machine learning models.
method Characterizes the tradeoff between fairness and accuracy, provides a post-processing algorithm.
result Post-processing algorithm yields optimal fair classifier when score is Bayes optimal.
Proposes a framework for balancing fairness and accuracy in data-restricted binary classification.
problem Balancing fairness and accuracy in applications with data restrictions.
method Directly analyzes the optimal Bayesian classifier's behavior under different data-restricting scenarios, formulating convex optimization problems.
result Demonstrates how accuracy of a Bayesian classifier is affected by fairness constraints in various data-restricting scenarios.
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.
Real-world applications of machine learning tools in high-stakes domains are often regulated to be fair, in the sense that the predicted target should satisfy some quantitative notion of parity with respect to a protected attribute. However, the exact tradeoff between fairness and accuracy is not entirely clear, even f…
Abstract reviews mathematical fairness in machine learning.
problem Ensuring fairness in machine learning models.
method Independence-based approach to fairness definitions and methodologies.
result Optimal fair classifiers and predictors under equality of odds are derived.
The paper proves statistical consistency and fairness guarantees for a plug-in algorithm.
problem Establishing statistical guarantees for fairness-aware binary classification.
method Proves statistical consistency and derives finite sample guarantees for the plug-in algorithm.
result The plug-in algorithm is statistically consistent and guarantees fairness and differential privacy.
New classifiers ensure fairness by adjusting a base classifier's operating characteristics.
problem Ensuring fairness in binary classification with multiple group constraints.
method Intervening directly on a base classifier's operating characteristics using group-wise ROC convex hulls and post-processing.
result Methods satisfy multiple fairness constraints (DP, EO, PP) with minimal interventions and near-oracle accuracy.
The paper explores fair regression and classification under demographic parity constraints.
problem Ensuring fairness in regression and classification models under demographic parity constraints.
method Characterizes the optimal fair regression function using a barycenter problem with optimal transport costs and studies the connection between fair classification and regression.
result The optimal fair regression function is derived from the solution to a barycenter problem with optimal transport costs, and the optimal fair cost-sensitive classifiers can be derived by applying thresholds to this function.
New algorithms handle missing data to improve fairness in machine learning.
problem Missing values in data can lead to unfair outcomes in machine learning models.
method Developed scalable and adaptive algorithms to handle missing values while preserving predictive information.
result Our adaptive algorithms consistently achieve higher fairness and accuracy than standard impute-then-classify methods.
Paper proposes an ensemble approach to improve fairness in classifier decisions.
problem Improving fairness in classifier decisions to prevent bias.
method Inspired by dropout techniques, feature drop-out is used to reduce classifier dependence on sensitive features while maintaining accuracy.
result An ensemble of classifiers with reduced sensitivity to sensitive features and improved accuracy.
Algorithmic fairness, and in particular the fairness of scoring and classification algorithms, has become a topic of increasing social concern and has recently witnessed an explosion of research in theoretical computer science, machine learning, statistics, the social sciences, and law. Much of the literature considers…
Framework for fair classification with noisy protected attributes and provable guarantees.
problem Fair classification with noisy protected attributes.
method Optimization framework for linear and linear-fractional fairness constraints, handling multiple non-binary attributes.
result Provably fair classifier with minimal accuracy loss, even with large noise.
Approach collects missing outcomes to improve fairness in classification.
problem Lack of true outcomes for incorrectly classified samples leads to biased classifiers.
method Exploration-based data collection to ensure all subpopulations are represented and fairness properties are encoded.
result Trained classifier converges to a fair classifier with bounded false positives.
New fairness criteria for algorithmic recourse actions that consider causal relationships.
problem Fairness of recourse actions in algorithmic classification.
method Proposes two new fairness criteria at group and individual levels, explicitly accounting for causal relationships.
result Fairness of recourse is complementary to fairness of prediction, and can be enforced by altering the classifier.
A test detects unfairness in machine learning classifiers.
problem Detecting and mitigating algorithmic biases in machine learning.
method Optimal transport theory to quantify and mitigate bias.
result Proposes a statistical test for detecting unfair classifiers.
Fairness constraints can improve accuracy from biased data.
problem Learning from biased training data can produce biased and suboptimal classifiers.
method Examined fairness-constrained ERM and other recovery methods.
result Equal Opportunity fairness constraint combined with ERM provably recovers Bayes Optimal Classifier under various bias models.
The potential for learned models to amplify existing societal biases has been broadly recognized. Fairness-aware classifier constraints, which apply equality metrics of performance across subgroups defined on sensitive attributes such as race and gender, seek to rectify inequity but can yield non-uniform degradation in…
Fairness-aware classification is receiving increasing attention in the machine learning fields. Recently research proposes to formulate the fairness-aware classification as constrained optimization problems. However, several limitations exist in previous works due to the lack of a theoretical framework for guiding the …
Fairness is a critical trait in decision making. As machine-learning models are increasingly being used in sensitive application domains (e.g. education and employment) for decision making, it is crucial that the decisions computed by such models are free of unintended bias. But how can we automatically validate the fa…
As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define individuals, but lack a discussion of certain features not being observed at test ti…
This work addresses fairness in ML models by training and evaluating attribute classifiers under uncertain and incomplete data.
problem Challenges in fairness metrics due to uncertain and incomplete data.
method Developed a theoretical and empirical analysis to understand and improve bias estimation in the data-scarce regime.
result The test accuracy of the attribute classifier is not always correlated with its effectiveness in bias estimation.
Paper studies fair classification of functional data.
problem Mitigating disparities in functional data classification.
method Unified framework for fairness-aware functional classification.
result Established theoretical guarantees on fairness and excess risk controls.
Unified framework for intersectionally fair AI models using MIO.
problem Bias in AI models for high-risk domains.
method Mixed-Integer Optimization (MIO) for fairness and interpretability.
result Improved performance in detecting and mitigating bias at intersections.
This work builds a fair classification algorithm that abstains from making predictions.
problem Building a fair classification algorithm that incorporates human decision-making and avoids disparities.
method Formalizes the problem of risk minimization under fairness and abstention constraints, derives the optimal classifier, and proposes a post-processing algorithm using unlabeled data.
result The proposed algorithm achieves fairness and abstention guarantees independently of the initial classifier, provided sufficient unlabeled data is available.
Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differenti…
New methods detect unfairness in multiclass classifiers using DCP.
problem Detecting unfairness in multiclass classifiers.
method Generalizes DCP to multiclass, provides optimization methods.
result Detects classifiers treating a significant fraction of the population unfairly.
We address the problem of algorithmic fairness: ensuring that sensitive variables do not unfairly influence the outcome of a classifier. We present an approach based on empirical risk minimization, which incorporates a fairness constraint into the learning problem. It encourages the conditional risk of the learned clas…
TaCo prevents non-linear classifiers from detecting sensitive attributes.
problem Ensuring fairness in NLP models by preventing sensitive attribute detection.
method Targeted Concept Erasure (TaCo) removes sensitive information from final latent representations, even against non-linear classifiers.
result TaCo outperforms state-of-the-art methods in reducing sensitive attribute prediction accuracy while preserving overall task performance.
Whereas previous post-processing approaches for increasing the fairness of predictions of biased classifiers address only group fairness, we propose a method for increasing both individual and group fairness. Our novel framework includes an individual bias detector used to prioritize data samples in a bias mitigation a…
FLEA makes fair classifiers robust against unreliable training data.
problem Fairness in machine learning from unreliable data sources.
method Filtering-based algorithm to identify and suppress unfair data sources.
result FLEA protects classifiers against corruptions as long as less than half of data sources are unreliable.
Recent work in fairness in machine learning has proposed adjusting for fairness by equalizing accuracy metrics across groups and has also studied how datasets affected by historical prejudices may lead to unfair decision policies. We connect these lines of work and study the residual unfairness that arises when a fairn…
Algorithmic decision making systems are ubiquitous across a wide variety of online as well as offline services. These systems rely on complex learning methods and vast amounts of data to optimize the service functionality, satisfaction of the end user and profitability. However, there is a growing concern that these au…