Empirical study on rich subgroup fairness for machine learning.
problem Ensuring fairness across large subgroups in machine learning.
method An algorithm that learns subject to rich subgroup fairness constraints.
result Rich subgroup fairness leads to large gains in fairness with mild accuracy costs.
A new algorithm COVA-FC improves subgroup-fair clustering efficiency.
problem Challenges in making cluster assignments independent of sensitive attributes in subgroups.
method Defining a subgroup-fairness gap, deriving a covariance-based surrogate, and introducing a continuous relaxation for efficient optimization.
result COVA-FC achieves competitive cost-fairness trade-offs and improves computational efficiency.
New algorithm tackles subgroup fairness in AI with multiple sensitive attributes.
problem Heavy computational burdens and data sparsity in subgroup fairness for multiple sensitive attributes.
method Doubly Regressing Adversarial learning (DRAF) for subgroup fairness, focusing on subgroups with sufficient sample sizes and marginal fairness.
result DRAF algorithm reduces a surrogate fairness gap for supIPM with less computation than directly reducing supIPM.
Proposes a new fairness definition for classifiers.
problem Ensuring fair classifiers with respect to sensitive features.
method Introduces a new fairness definition that generalizes existing proposals, allowing for generic sensitive features and convex objectives.
result Proposes a convex fairness-aware objective based on minimising conditional value at risk (CVaR).
PEF identifies the best subgroup performance balance for fairness.
problem Fairness constraints can degrade performance in skewed datasets.
method PEF identifies the closest operating point on the Pareto curve of subgroup performances.
result PEF achieves Pareto levels in accuracy for all subgroups.
Proposes a method to learn fair predictors for multiple subgroups with limited data.
problem Fairness and accuracy issues in learning from multiple subgroups with limited data.
method Formulates a bilevel objective to learn subgroup-specific predictors and a fair predictor that is close to all of them.
result The method effectively controls group sufficiency and generalization error, improving fairness and accuracy.
The paper tackles fairness in forecasting and learning linear dynamical systems.
problem Under-representation bias in training data for multiple subgroups.
method Introducing subgroup-fair and instant-fair learning of LDS from multiple trajectories of varying lengths, using hierarchies of convexifications of non-commutative polynomial optimisation problems.
result Empirical results show both the beneficial impact of fairness considerations on statistical performance and encouraging effects of exploiting sparsity on run time.
The paper explores fairness in machine learning by setting subgroup sample complexity bounds and advocating for human intervention.
problem Machine learning models often show different performance metrics for different subgroups, due to various factors.
method The paper presents lower bounds of subgroup sample complexity for metric-fair learning and proposes an approach using individual fairness definitions for cases where subgroup samples are insufficient.
result For a classifier to be fair, adequate subgroup population samples are necessary, and model dimensionality must align with subgroup population distributions.
Improves fairness in machine learning by adding underrepresented group data.
problem Machine learning biases across subgroups due to under-representation or societal biases.
method Data augmentation via pairwise mixup across subgroups to balance subpopulations.
result Achieves fair outcomes with robust if not improved accuracy.
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.
Algorithm learns fair representations that can be easily modified.
problem Group and subgroup fairness with multiple sensitive attributes.
method Disentangled representation learning for flexible fairness.
result Flexible fair representations enable easy adaptation to new tasks.
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.
This paper evaluates fairness in deep metric learning and proposes a method to reduce subgroup performance gaps.
problem The negative impact of deep metric learning representations on minority subgroup performance in downstream tasks.
method Definition of fairness in DML through inter-class, intra-class, and uniformity properties; finDML benchmark; Partial Attribute De-correlation (PARADE) method.
result Bias in DML representations propagates to downstream tasks, even with balanced training data.
The paper introduces a model to measure ASR fairness, addressing key issues.
problem Measuring fairness in ASR systems for different subgroups.
method Mixed-effects Poisson regression to control nuisance factors and handle unobserved heterogeneity.
result The method effectively addresses WER gaps among subgroups and is flexible for practical analyses.
Study binary choice with asymmetric loss, offering simple solutions.
problem Binary choice with asymmetric loss in data-rich environments.
method Loss-based reweighting of logistic regression or machine learning techniques.
result Valid decisions on binary outcomes with general loss functions.
A new method improves AI fairness assessment by estimating performance across intersectional subgroups.
problem Limited evaluation of AI systems across intersectional subgroups due to small sample sizes.
method Structured regression approach to disaggregated evaluation.
result Our method yields more accurate performance estimates, especially for small subgroups.
New technique reduces gender discrimination in credit lending models.
problem Bias and unfairness in credit lending predictions.
method Subgroup Threshold Optimizer (STO) technique.
result Reduces gender discrimination by over 90%.
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.
Selective regression allows abstention to improve fairness criteria.
problem Selective regression can exacerbate disparities between subgroups.
method Proposes new fairness criteria and two approaches to mitigate performance disparity.
result Proposed fairness criteria ensures performance improvement for every subgroup with reduced coverage.
Fairness in machine learning increases privacy risks, especially for underrepresented groups.
problem Privacy risks in fair machine learning models, particularly for underrepresented groups.
method Membership inference attacks to measure information leakage and analyze fairness vs. privacy trade-offs.
result Achieving fairness in machine learning models increases privacy risks, especially for underrepresented groups.
The paper develops methods to create fair and transferable representations without subgroup discrimination.
problem Creating fair and transferable representations without discriminating subgroups in the population.
method The approach involves modifying data representations to meet fairness constraints, leveraging task similarities via low rank matrix factorization.
result The learned fair representation transfers well to novel tasks, improving prediction performance and fairness metrics.
The paper offers simple, near-optimal algorithms for multi-group learning.
problem Learning predictors within subgroups of a population, addressing fairness and hidden stratification.
method Studies the structure of solutions and provides simple, near-optimal algorithms.
result Simple and near-optimal algorithms for multi-group learning.
Fair k-means algorithm ensures equitable costs for different groups.
problem K-means clustering can result in biased outcomes for subgroups of data.
method Presented a fair k-means objective and algorithm (Fair-Lloyd) to choose cluster centers that provide equitable costs for different groups.
result Fair-Lloyd algorithm ensures all groups have equal costs in the output k-clustering, with negligible increase in running time.
Develops a new criterion for subgroup fairness in algorithmic decision support.
problem Identifying fair recommendations in algorithms despite group-level differences.
method IJDI criterion and IJDI-Scan approach to detect and mitigate disparities.
result Identifies significant disparities in recommendations across subpopulations.
FairVis helps discover biases in machine learning models.
problem Discovering biases in machine learning models is challenging due to multiple definitions of fairness and numerous subgroups.
method Integrates a novel subgroup discovery technique with a mixed-initiative visual analytics system.
result Demonstrates how FairVis helps discover biases in real datasets.
Unified framework TERM improves fairness and robustness.
problem Outliers and subgroup fairness in empirical risk minimization.
method Unified framework TERM with a hyperparameter tilt.
result TERM improves fairness and robustness.
The paper tackles fairness in overlapping populations using online learning techniques.
problem Improving fairness to subgroups in settings with overlapping populations and sequential predictions.
method The approach draws from the sleeping experts literature in online learning to achieve a goal of unweighted average of false negative and false positive rate for overlapping populations.
result It shows that satisfying the guarantee for multiple overlapping groups is not straightforward and can be statistically impossible even when predictors perform well separately on each subgroup.
This primer tackles biases in machine learning for image analysis, proposing solutions.
problem Causal and statistical biases in machine learning methods for image analysis.
method Introduction of causal and statistical structures that induce failure, highlighting two problems: no fair lunch and subgroup separability.
result Current fair representation learning methods fail to solve these problems, suggesting new paths forward.
Proposes a method to achieve quantile fairness in predictions.
problem Lack of research on quantile fairness in socially sensitive domains.
method Introduces a framework to learn a real-valued quantile function under Demographic Parity fairness.
result Demonstrates superior empirical performance and uncovering fairness-accuracy trade-offs.
We propose a fair principal component analysis method that balances reconstruction error and subgroup fairness.
problem Fairness and robustness in principal component analysis for consequential domains.
method Distributionally robust optimization over the Stiefel manifold with a Riemannian subgradient descent.
result The proposed method achieves better performance on real-world datasets compared to state-of-the-art baselines.
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.
ROME improves algorithmic fairness by learning latent group structure robustly.
problem Latent subgroup disparities and distribution shifts in machine learning models.
method ROME uses an Expectation-Maximization algorithm for linear models and a neural Mixture-of-Experts for nonlinear settings.
result ROME significantly improves fairness compared to standard methods while maintaining average performance.
Randomized predictions ensure fair and accurate individual calibration in machine learning.
problem Systematic bias in typical calibration methods leads to unfair predictions for certain subgroups.
method Randomization of predictions to enforce individual calibration, trading off bias with variance.
result Randomized regression functions are more calibrated for arbitrary subgroups and achieve higher utility.
Study fairness in vaccine allocation in social networks.
problem Fairness implications of vaccine allocation strategies in social networks.
method Defined precision disease control problem, used ML Fairness Gym to simulate and analyze.
result Different treatment strategies distribute disease burden differently across subgroups.
Algorithm learns fair representations without sacrificing accuracy across groups.
problem Mitigating disparity among different demographic subgroups in classification.
method Balanced error rate and conditional alignment of representations.
result Improves utility-fairness trade-off on balanced datasets.
FlipTest detects discrimination in classifiers using optimal transport.
problem Detecting discrimination in classifiers without causal information.
method Optimal transport to match individuals in different protected groups, creating similar pairs of in-distribution samples.
result FlipTest identifies subgroups that may be harmed by model discrimination, even when the model satisfies group fairness criteria.
New framework tackles fairness in link prediction beyond demographic parity.
problem Systemic biases in link prediction can exacerbate societal inequalities.
method Formalizes limitations of existing fairness evaluations and proposes a new framework.
result Proposes a lightweight post-processing method combined with decoupled link predictors.
The paper explores fairness metrics in automated decision-making and their limitations.
problem Discrimination in automated resource allocation decisions.
method Analysis of fairness metrics and distributive justice principles.
result Prominent fairness metrics fail to address egalitarian and sufficiency concerns in resource allocation.
FairGround offers a diverse dataset corpus for fair ML research.
problem Lack of diverse, well-annotated datasets in fair ML research.
method Unified framework and Python package for reproducible fair ML research.
result Advances reproducibility and generalizability of fair ML research.
We found hidden convexity in FPCA and developed a faster algorithm.
problem Bias in PCA leading to unequal subgroup outcomes.
method Convex optimization via eigenvalue optimization.
result Faster and fairer PCA algorithm.
FIFA improves fairness in imbalanced datasets by encouraging both classification and fairness generalization.
problem Imbalanced datasets lead to poor fairness generalization in classifiers.
method FIFA: Imbalance-Fairness-Aware approach that encourages both classification and fairness generalization.
result FIFA improves fairness generalization on real-world datasets.
Secure methods learn fair models without revealing sensitive attributes.
problem Training fair machine learning models without exposing sensitive data.
method Secure multi-party computation to encrypt sensitive attributes.
result Outcome-based fair models can be learned, checked, or verified without revealing sensitive attributes.
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.
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.
Study fair healthcare predictions without harming patients.
problem Balancing fairness and avoiding unnecessary harm in healthcare predictions.
method Formalizes Pareto-optimal approach to minimize risk disparity without causing harm, dynamically re-balancing subgroup risks.
result Demonstrates a method to train neural networks achieving fair predictions without unnecessary harm.
Paper introduces MinDiff framework for balancing classifier performance and fairness.
problem Balancing classifier performance and fairness in machine learning models.
method MinDiff framework with kernel-based statistical dependency tests.
result Demonstrates real-world improvements in classifier performance and fairness.
FairGP uses graph partitioning to make Graph Transformers fair and scalable.
problem Fairness issues in Graph Transformers, especially against sensitive features.
method Graph partitioning to minimize the influence of higher-order nodes and optimize attention mechanisms.
result FairGP improves fairness in Graph Transformers while reducing computational complexity.
Algorithm learns fair ranking from biased data.
problem Unfair ranking policies from biased implicit feedback.
method Policy-gradient approach with amortized fairness constraints.
result Efficient algorithm FULTR learns fair policies.