MMD-B-Fair learns fair representations by minimizing MMD test power.
problem Learning fair representations of data while preserving target attributes.
method Kernel two-sample testing and block testing schemes.
result Minimizing MMD test power allows hiding sensitive attribute information.
Framework tests group fairness in machine learning models.
problem Detecting biases in machine learning classifiers.
method Optimal transport projections to audit group fairness.
result Statistical test for various fairness notions efficiently computed.
Synthetic data mimics real-world demographics for fairness testing.
problem Lack of complete, representative datasets for fairness testing.
method Construct synthetic datasets using overlapping real and separate datasets.
result Synthetic data yields consistent fairness metrics with real data.
Commentary on Cheng's fairness comparison between tests and AI.
problem Distinction between equality and equity in fairness.
method Systematic comparison of test fairness and algorithmic fairness.
result Importance of causality in fairness research.
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.
fAux tests individual fairness without domain knowledge or out-of-domain samples.
problem Testing for individual fairness in machine learning models.
method Derivative comparison between model predictions and auxiliary model predictions.
result Effectively identifies discrimination on synthetic and real-world datasets.
Propensity score matching improves fairness in machine learning models.
problem Bias in training data affects fairness metrics in machine learning models.
method Propensity score matching to evaluate and mitigate bias in test data.
result FairMatch significantly reduces bias in test data without sacrificing predictive performance.
Framework certifies fairness of machine learning models interactively and privately.
problem Certifying fairness of machine learning models in privacy-preserving scenarios.
method Interactive test with cryptographic techniques for fairness certification.
result Empirical evaluation of fairness for various models and definitions.
New tools for assessing and correcting bias in AI algorithms.
problem Fairness and bias in AI algorithms, especially when ground truth data is unavailable.
method Three tools: controlled fairness, retraining algorithms, and parameter adjustment algorithms.
result Effective in reducing bias and improving fairness in AI models.
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 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…
The paper proposes a method to identify fair features in ML data integration.
problem Ensuring fairness in machine learning data integration.
method Causal interventional fairness, conditional independence tests, group testing.
result The proposed algorithm identifies fair features without biasing the dataset.
Statistical tests for fairness in admissions data reveal hidden patterns.
problem Simpson's paradox in admissions data hides true gender bias.
method Introduces a new statistical test based on Pearl's instrumental-variable inequalities.
result Statistical tests for fairness coincide with causal notions for the Berkeley admissions case.
Fair machine learning models can be vulnerable to adversarial attacks that reduce their accuracy and fairness.
problem Fairness constraints in machine learning models can compromise their robustness against adversarial attacks.
method Analysis of data poisoning attacks on group-based fair machine learning models, focusing on equalized odds.
result Adversaries can significantly reduce the test accuracy of fair machine learning models and widen their fairness gap.
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.
The study tests and optimizes fairness in credit scoring models.
problem Discrimination in credit scoring models based on protected attributes.
method Formal testing and variable identification to optimize fairness and performance.
result Guidance on monitoring and improving algorithmic fairness in credit scoring.
Unified framework for fair decision-making across diverse groups.
problem Statistical brittleness in fairness testing for small subgroups.
method Size-adaptive hypothesis testing framework.
result Validated approach for interpretable, statistically rigorous decisions.
The paper discusses fairness in bank stress tests, comparing various methods to address institutional differences.
problem Fair aggregation of bank-specific stress test models into a common model.
method Comparing various notions of regression fairness, including estimating and discarding centered bank fixed effects.
result The method of estimating and discarding centered bank fixed effects is preferable for linear models, improving forecast accuracy and equal treatment.
New approach for fair predictions under changing data distributions.
problem Fairness in classification algorithms under covariate shift.
method Proposes a robust predictor that satisfies fairness and maintains statistical properties of source data.
result Demonstrates improved fairness and target performance on benchmark tasks.
Securely trains fair models using homomorphic encryption.
problem Protecting sensitive features while testing model fairness.
method Fully homomorphic encryption for training and testing.
result Practical application to adult income data set.
We study the problem of learning fair prediction models for unseen test sets distributed differently from the train set. Stability against changes in data distribution is an important mandate for responsible deployment of models. The domain adaptation literature addresses this concern, albeit with the notion of stabili…
The paper tackles individual fairness in ML models, developing statistical methods to detect bias.
problem Detecting and measuring violations of individual fairness in machine learning models.
method Formalizing the problem as adversarial attack, developing inference tools for the adversarial cost function.
result Statistical methods to assess and test hypotheses of model fairness with non-coverage error rate control.
We propose an approach to fair classification that enforces independence between the classifier outputs and sensitive information by minimizing Wasserstein-1 distances. The approach has desirable theoretical properties and is robust to specific choices of the threshold used to obtain class predictions from model output…
New framework for interpreting disaggregated fairness evaluations using causal models.
problem Misinterpretation of disaggregated fairness evaluations due to data representativeness and selection bias.
method Causal graphical models to characterize fairness properties and metric stability under different data generating processes.
result Disaggregated evaluations are unreliable without explicit assumptions regarding bias mechanisms.
Proposes a fair machine learning framework robust to distribution shifts without causal graph knowledge.
problem Fairness issues in machine learning models under distribution shifts.
method Stochastic distributionally robust optimization with Exponential Renyi Mutual Information (ERMI) fairness measure.
result First stochastic framework for fair learning robust to distribution shifts without causal graph knowledge.
We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group labels, either at training or runtime. To address this, we investigate improving fairness metrics for …
Motivated by settings in which predictive models may be required to be non-discriminatory with respect to certain attributes (such as race), but even collecting the sensitive attribute may be forbidden or restricted, we initiate the study of fair learning under the constraint of differential privacy. We design two lear…
We develop a theory which applies to any market dynamics that satisfy a fair market assumption on the nullity of the average profit of simple market making strategies. We show that for any such fair market, there exists a martingale fair price which corresponds to the average liquidation value (at the ask or the bid) o…
CST detects discrimination by comparing protected and non-protected individuals with a counterfactual.
problem Detecting discrimination in classifiers using legal fairness conditions.
method Operationalizes fairness given the difference using counterfactual reasoning.
result CST uncovers more discrimination cases than traditional situation testing.
Proposes a fairness criterion for multi-objective optimization in classification.
problem Ensuring fairness in classification models across different groups.
method Formulates a minimax Pareto fairness criterion and provides an optimization algorithm.
result Demonstrates improved fairness compared to existing methods on various real-world datasets.
FairVIC improves fairness in neural networks without sacrificing accuracy.
problem Mitigating bias in automated decision-making systems, particularly in deep learning models.
method Integrates variance, invariance, and covariance terms into the loss function during training to abstract fairness concepts.
result Significant improvements in fairness across all tested metrics without compromising accuracy.
The paper provides CI for test unfairness of group-fairness-aware classifiers trained with online SGD.
problem Ensuring fairness in machine learning models trained with stochastic gradient descent.
method Developed an online multiplier bootstrap method to estimate CI for test unfairness of DI and DM-aware linear classifiers.
result Asymptotic Central Limit Theorem holds for CI estimation of DI and DM-aware models.
Develops algorithm to make fair decisions from biased data.
problem Ethical concerns in machine learning fairness.
method Fair Learning through Data Preprocessing (FLAP) algorithm.
result Counterfactual fairness equivalent to conditional independence.
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.
Framework for fair predictive models using resampled sensitive attributes.
problem Achieving fair predictions in machine learning models.
method Introducing a discrepancy functional and resampling sensitive attributes.
result Improved performance and equitable uncertainty quantification.
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.
A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease with increased fairness. Novel to this work, we examine fair classification through the lens of mismatched hypothesis testing: trying …
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.
COMMOD debiases models with minimal and interpretable changes.
problem Inconsistent and costly model updates in fair machine learning.
method Introduced COMMOD, a novel algorithm for algorithmic fairness that minimizes changes and makes them interpretable.
result COMMOD achieves comparable performance to state-of-the-art debiasing methods while making minimal and interpretable changes.
Develops a new fairness learning approach for multi-task regression models.
problem Fairness in multi-task regression models with biased datasets.
method Uses rank-based non-parametric independence test (Mann Whitney U statistic) and reformulates as non-convex optimization problem.
result Outperforms state-of-the-art methods on fairness metrics.
Paper examines fairness of data augmentation methods, finding vanilla Mixup outperforms Fair Mixup.
problem Improving fairness in classification models with limited minority data.
method Uses multicalibration to rigorously evaluate and improve data augmentation methods for classification fairness.
result Vanilla Mixup outperforms Fair Mixup and baseline methods in fairness and accuracy, especially with small minority groups.
This paper is about two related decision theoretic problems, nonparametric two-sample testing and independence testing. There is a belief that two recently proposed solutions, based on kernels and distances between pairs of points, behave well in high-dimensional settings. We identify different sources of misconception…
Machine learning algorithms have been increasingly deployed in critical automated decision-making systems that directly affect human lives. When these algorithms are only trained to minimize the training/test error, they could suffer from systematic discrimination against individuals based on their sensitive attributes…
We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruc…
CAP adapts optimization to class attributes for better fairness.
problem Heterogeneities across classes impede classification performance.
method CAP generates class-specific learning strategies based on attributes.
result CAP improves over naive approach and is competitive with prior art.
We tackle the problem of algorithmic fairness, where the goal is to avoid the unfairly influence of sensitive information, in the general context of regression with possible continuous sensitive attributes. We extend the framework of fair empirical risk minimization to this general scenario, covering in this way the wh…
Computers are increasingly used to make decisions that have significant impact in people's lives. Often, these predictions can affect different population subgroups disproportionately. As a result, the issue of fairness has received much recent interest, and a number of fairness-enhanced classifiers and predictors have…
This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework), testing workflow (e.g., test generation and test evaluation), and …