Adversarial training can lead to unfair accuracy disparities between different groups.
problem Adversarial training algorithms introduce unfair accuracy disparities between different groups of data.
method Propose a Fair-Robust-Learning (FRL) framework to mitigate unfairness in adversarial defenses.
result Empirical and theoretical validation of FRL's effectiveness in mitigating unfairness.
Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the e…
Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy. We demonstrate that in the neural networks trained using differentially private …
Paper tackles fairness in CCA by minimizing correlation disparity error.
problem Fairness issues in CCA.
method Framework to minimize correlation disparity error in CCA.
result Reduces correlation disparity error without sacrificing CCA accuracy.
Machine learning models (e.g., speech recognizers) are usually trained to minimize average loss, which results in representation disparity---minority groups (e.g., non-native speakers) contribute less to the training objective and thus tend to suffer higher loss. Worse, as model accuracy affects user retention, a minor…
New method detects and prevents unfairness in few-shot regression models.
problem Fairness issues in supervised few-shot meta-learning models.
method Causal Bayesian knowledge graph for dependency visualization, risk difference quantification, and fast-adapted bias-control approach.
result Efficiently detects and mitigates unfairness in model predictions.
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.
Introduces causal fairness analysis to address unfairness in AI decisions.
problem Fairness issues in AI decision-making.
method Link observed disparities to underlying causal mechanisms.
result Develops Fairness Map and Fairness Cookbook.
Paper proposes a federated learning framework for relative fairness.
problem Traditional fairness in federated learning overlooks performance disparities between client subgroups.
method Uses a minimax problem approach to minimize relative unfairness, introducing a fairness index based on loss ratios.
result Empirical evaluations confirm the framework's effectiveness in maintaining model performance while reducing disparity.
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.
Conformal prediction sets can lead to unfair outcomes.
problem Disparate impact in decision-making with conformal prediction sets.
method Experiments with human participants to demonstrate disparate impact and propose equalizing set sizes across groups.
result Providing prediction sets that satisfy Equalized Coverage increases disparate impact compared to marginal coverage.
New clustering method considers causal fairness to avoid bias.
problem Clustering algorithms can unintentionally propagate unfair disparities.
method Integrates causal fairness metrics into clustering algorithms.
result Demonstrates efficacy on datasets with known unfair biases.
The paper studies and mitigates accuracy disparity in regression models.
problem Accuracy disparity between different demographic subgroups in high-stakes domains.
method Error decomposition theorem and distribution alignment algorithm.
result The proposed algorithm effectively mitigates accuracy disparity while maintaining predictive power.
Examines fairness in ML for health, highlighting its importance and challenges.
problem Ensuring fairness in ML models for health to prevent health disparities.
method Reviews fairness notions in ML for health, including group, individual, and causal-based approaches.
result Discusses the importance and challenges of fairness in health-focused ML applications.
In recent years, automated data-driven decision-making systems have enjoyed a tremendous success in a variety of fields (e.g., to make product recommendations, or to guide the production of entertainment). More recently, these algorithms are increasingly being used to assist socially sensitive decision-making (e.g., to…
Optimal LDP mechanisms reduce data unfairness in classification.
problem Reducing data unfairness in classification models.
method Developed a closed-form optimal mechanism for binary attributes and a tractable framework for multi-valued attributes.
result Optimal LDP mechanisms improve fairness in classification while maintaining accuracy close to non-private models.
This paper tackles fair Bayes-optimal classifiers under predictive parity, proving their limitations and proposing a new algorithm.
problem Ensuring fair Bayes-optimal classifiers under predictive parity, especially when group performance levels vary widely.
method Proving the limitations of fair Bayes-optimal classifiers under predictive parity and proposing a new adaptive thresholding algorithm, FairBayes-DPP.
result Fair Bayes-optimal classifiers under predictive parity may not hold if group performance levels vary widely, leading to within-group unfairness.
The paper tackles fair policy targeting by optimizing allocation rules to minimize unfairness.
problem Discrimination in individualized treatments of social welfare programs.
method Formulated as a mixed-integer linear program, solved using off-the-shelf algorithms, derived regret bounds and small sample guarantees.
result Designs fair and efficient treatment allocation rules within the Pareto frontier.
The paper examines how adversarial robustness affects accuracy disparity across different classes.
problem Understanding the impact of adversarial robustness on accuracy disparity across different classes.
method Linear classifiers under a Gaussian mixture model, decomposing the impact into inherent and imbalance effects.
result Adversarial robustness consistently degrades standard accuracy in balanced classes, but the class imbalance ratio plays a different role in accuracy disparity.
Develops algorithm to reduce real-world inequality.
problem Reduces inequality in real-world disparities.
method Impact remediation framework using social science insights and constrained optimization.
result Optimal intervention policies discovered to improve equity.
Machine Learning techniques have become pervasive across a range of different applications, and are now widely used in areas as disparate as recidivism prediction, consumer credit-risk analysis and insurance pricing. The prevalence of machine learning techniques has raised concerns about the potential for learned algor…
The paper tackles fairness in data and algorithms, expanding on prior work.
problem Discrimination and disparate treatment in data and algorithms.
method Targeted learning for nonparametric inference of fairness in the data generating process.
result Derivation and validation of estimators for fairness metrics like demographic parity and equal opportunity.
Selective classification can worsen accuracy disparities between groups.
problem Selective classification can magnify existing accuracy disparities between various groups.
method Study of margin distribution and distributionally-robust models.
result Selective classification can uniformly improve each group on distributionally-robust models.
Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine…
The paper proposes a fair reinforcement learning framework to prevent healthcare disparities.
problem Unfair reinforcement learning policies in healthcare can lead to socioeconomically-disadvantaged subgroups being underprivileged.
method The paper introduces a counterfactual fairness framework and a sequential data preprocessing algorithm to achieve fair sequential decision making.
result The proposed approach greatly enhances fair access to counseling in a digital health dataset designed to reduce opioid misuse.
New research shows machine-assisted decisions can still be unfair even when the algorithm is fair.
problem Ensuring fairness in decisions made with machine-assisted human input.
method Formal model and lab experiment to analyze how machine predictions affect human decisions.
result Excluding information about protected groups from machine predictions can increase disparities.
New method reduces privacy impact on model accuracy for underrepresented groups.
problem Privacy mechanisms disproportionately affect underrepresented groups in machine learning models.
method Proposes DPSGD-F, a modified DPSGD that adjusts group contributions based on clipping bias.
result DPSGD-F removes disparate impact of differential privacy on model accuracy for protected groups.
The paper explores fair predictors in supervised learning using IPMs and Kolmogorov distance.
problem Achieving fairness in supervised learning with significant demographic effects.
method Identifying conditions for SP-fair predictors and using IPMs to measure unfairness.
result Fair predictors can improve accuracy and are computationally efficient.
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.
Proposes a fair classification model using robust optimization.
problem Preventing discrimination in classification models.
method Distributionally robust logistic regression with Wasserstein ball and convex unfairness measure.
result Improves fairness with minimal loss in predictive accuracy.
Paper explores fair classification with bounded disparity using finite datasets.
problem Ensuring fairness in binary classification with protected groups.
method Minimax optimal approach with fairness constraints and demographic disparity control.
result Proposes FairBayes-DDP+ method that achieves minimax lower bound on fairness-aware excess risk.
This paper tackles fairness in PCA by balancing it with reconstruction error.
problem Fairness concerns in PCA due to different group representation errors.
method A multi-objective optimization approach to balance fairness and reconstruction error.
result Achieving fairness with minimal loss in reconstruction error.
New fair regression method improves fairness in chronic kidney disease classification.
problem Mitigating societal bias in health care for multiple groups.
method Penalized fair regression framework for multiple groups, with penalties for true positive rate disparity.
result Achieves fairness-accuracy frontier beyond existing methods in simulations and real-world data.
New approach to fairness in machine learning models using conformal prediction.
problem Fairness in machine learning models' downstream decision-making.
method Theoretical derivation and empirical evaluation of label-clustered conformal prediction.
result Label-clustered conformal prediction often provides a favorable balance between utility and substantive fairness.
This work uncovers how model and data biases interact to cause unfairness in fraud detection.
problem Unfairness in fraud detection algorithms due to model and data biases.
method Taxonomy of data bias, hypotheses on fairness-accuracy trade-offs, real-world fraud use case study.
result Data bias affects fairness in expected value and variance, and simple pre-processing can balance group-wise error rates.
A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In this paper, we provide an in-depth study of the phenomenon of disparate vulnerability against MIAs: unequal success rate of MIAs against diff…
We present a new approach for mitigating unfairness in learned classifiers. In particular, we focus on binary classification tasks over individuals from two populations, where, as our criterion for fairness, we wish to achieve similar false positive rates in both populations, and similar false negative rates in both po…
Following related work in law and policy, two notions of disparity have come to shape the study of fairness in algorithmic decision-making. Algorithms exhibit treatment disparity if they formally treat members of protected subgroups differently; algorithms exhibit impact disparity when outcomes differ across subgroups,…
Paper proposes a new algorithm to minimize AUC disparities in machine learning models.
problem Minimizing unfairness in AUC scores for machine learning models.
method Proposes a minimax learning and bias mitigation framework for AUC optimization.
result Proves the convergence of the proposed algorithm to minimize group-level AUC.
CCI combines Bayesian and gradient boosting to create fair, reliable credit risk scores.
problem Tackles high-stakes lending decisions with changing data distributions and fairness constraints.
method Combines Bayesian neural risk scorer and fairness-constrained gradient boosting with shift-aware fusion.
result CCI achieves best trade-off between discrimination, calibration, stability, and fairness.
Study shows label errors impact model disparity metrics, proposing mitigation methods.
problem Impact of label errors on model disparity metrics.
method Empirical study, characterizing label error effects; proposing estimation and relabeling methods.
result Label errors significantly affect model disparity metrics, particularly for minority groups.
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…
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.
Machine learning models are widely adopted in scenarios that directly affect people. The development of software systems based on these models raises societal and legal concerns, as their decisions may lead to the unfair treatment of individuals based on attributes like race or gender. Data preparation is key in any ma…
This work addresses local fairness in machine learning models.
problem Ensuring fairness within subregions of feature space, not just global averages.
method Introduces ROAD, a Distributionally Robust Optimization (DRO) approach with adversarial learning.
result Achieves Pareto dominance in local fairness and accuracy across datasets.
FAIRIF improves fairness in deep learning models without changing the model architecture.
problem Improving fairness in deep learning models trained on sensitive data.
method Two-stage training algorithm that minimizes loss over a reweighted data set, balancing model performance across demographic groups.
result FAIRIF reduces disparity among different groups in classification settings, improving fairness-utility trade-offs.
Semi-supervised learning benefits the rich more than the poor, affecting fairness.
problem Disparate impact of semi-supervised learning on different sub-populations.
method Theoretical and empirical analysis of a broad family of SSL algorithms using pseudo-labels.
result Semi-supervised learning benefits the rich more than the poor, potentially violating fairness.
When the performance of a machine learning model varies over groups defined by sensitive attributes (e.g., gender or ethnicity), the performance disparity can be expressed in terms of the probability distributions of the input and output variables over each group. In this paper, we exploit this fact to reduce the dispa…