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.
New research shows transparent treatment disparity is better for achieving impact parity.
problem Achieving impact parity in ML models when group membership is correlated with other features.
method Theoretical analysis and experimental testing of disparate learning processes (DLPs).
result DLPs can lead to unintended treatment disparity and within-class discrimination, undermining impact parity.
The paper introduces return parity for fairness in MDPs, addressing delayed and adverse effects.
problem Fairness in MDPs for dynamic domains with delayed and adverse effects.
method Proposes return parity, decomposes return disparity, and develops algorithms for state visitation distributional alignment.
result The proposed algorithms can successfully close the disparity gap while maintaining policy performance.
Study shows explanation disparities in machine learning models are influenced by data and model properties.
problem Disparities in post-hoc machine learning explanation methods across race and gender.
method Simulations and experiments on a real-world dataset to assess challenges to explanation disparities.
result Increased covariate shift, concept shift, and omission of covariates increase explanation disparities, especially for neural network models.
Machine learning models can lead to group representation disparity, affecting long-term retention.
problem Representation disparity in ML models can lead to group retention issues over time.
method Analyzed user dynamics and fairness criteria in a sequential decision-making framework.
result Representation disparity can worsen over time without proper fairness criteria.
DCEM algorithm reduces bias in machine learning models trained on selective labels.
problem Bias in machine learning models trained on selective labels.
method Disparate Censorship Expectation-Maximization (DCEM) algorithm.
result DCEM improves bias mitigation without sacrificing discriminative performance.
What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, g…
FairWASP optimizes training data to reduce disparities across subgroups.
problem Reducing disparities in model outputs across different subgroups in machine learning.
method A novel pre-processing approach that minimizes Wasserstein distance to the original dataset while satisfying demographic parity.
result Integer weights are optimal, allowing FairWASP to be understood as duplicating or eliminating samples.
The paper compares fairness criteria in algorithmic decision-making.
problem Fairness in machine learning algorithms can lead to biases and disparities.
method The study examines three fairness criteria: Color-blind, Demographic Parity, and Equalized Odds.
result Equalized Odds (EO) is the only criterion that removes group-level disparity.
The paper offers methods for testing disparate impact using confidence intervals.
problem Testing for disparate impact in machine learning.
method Asymptotic distribution of indexes and use of confidence intervals.
result The importance of using confidence intervals over single values in testing disparate impact.
Combines multi-task and semi-supervised learning for disparate label spaces.
problem Sequence classification tasks with multiple, unrelated label sets.
method Joint embedding space and transfer functions between label embeddings.
result Outperforms strong baselines in topic-based sentiment analysis.
Optimal pre-processing reduces disparate impact by minimizing total variation distance.
problem Achieving fairness in data outputs based on protected attributes.
method Using pre-processing to enforce fairness, minimizing total variation distance between pre-processed and original data distributions.
result The problem of fairness can be formulated as a linear program, efficiently solvable.
End-to-end framework learns precise disparity for activity recognition.
problem Precise portrayal of intraclass disparity in activity recognition.
method Knowledge-directed adversarial learning framework with two competitive encoding distributions.
result Robust and generalizable performance on HAR benchmark datasets.
Paper finds sharpness differences in transformer blocks accelerating LLM training.
problem Understanding and accelerating large language model pre-training.
method Uncovering sharpness disparity across transformer blocks and proposing Blockwise Learning Rate.
result Blockwise Learning Rate strategy accelerates LLM pre-training with lower loss and speedup.
Study shows unequal success of membership inference attacks across different groups.
problem Unequal success of membership inference attacks across different groups.
method Established conditions for preventing MIAs and derived connections to fairness and differential privacy.
result Estimating disparate vulnerability to MIAs can lead to overestimation; suitable attacks and statistical framework provided.
The paper compares different fairness definitions under various worldviews.
problem Avoiding disparity amplification under different worldviews.
method Mathematical comparison of four fairness definitions using a theoretical framework.
result Different worldviews require different fairness definitions to avoid disparity amplification.
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.
New method improves fairness in biased predictions.
problem Improving fairness in biased classifier predictions.
method Individual bias detector prioritizes data samples for a bias mitigation algorithm.
result Superior performance in individual and group fairness on real-world datasets.
The paper analyzes and corrects disparate impact in machine learning models using information theory.
problem Systematic discrimination in machine learning models based on sensitive attributes.
method Information-theoretic framework to quantify and correct disparate impact.
result Closed-form expressions for efficient correction of input distributions to achieve statistically indistinguishable output distributions.
Two-stage algorithm removes bias in machine learning decisions.
problem Bias in machine learning decisions can unfairly discriminate specific groups.
method Inspired by two-stage least squares, a two-stage algorithm that removes bias in training data.
result The algorithm avoids disparate impact when making decisions.
The paper addresses fairness in machine learning by adjusting input distributions.
problem Reducing disparate impact in machine learning models over different groups.
method The approach involves learning a counterfactual distribution to adjust input variables for disadvantaged groups.
result The method can reduce disparate impact without training a new model.
Bayesian model identifies health disparities in disease progression.
problem Health disparities bias disease progression models.
method Interpretable Bayesian model accounting for three disparities.
result Model identifies and corrects for health disparities.
Study decomposes racial healthcare disparities via shifts in mediator distributions.
problem Racial disparities in healthcare expenditures and their underlying drivers.
method Framework decomposing disparities into mediator distribution shifts and residual components, using MEPS data.
result Substantial disparities persist even when mediators are equalized, suggesting unmeasured or structural factors.
New method evaluates multiple social disparities using machine learning.
problem Reduction of educational disparities across multiple dimensions.
method Triply-Robust Machine Learning Approach for Causal Decomposition Analysis.
result Simultaneous interventions across multiple domains reduce disparities.
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…
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.
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.
Study highlights fairness issues in travel behavior prediction models.
problem Ethical challenges in travel behavior analysis using machine learning.
method Operationalized computational fairness by equality of opportunity; compared DNN and DCM; introduced absolute correlation regularization.
result Both DNN and DCM predict disparities across social groups, with DNN outperforming DCM in prediction disparities.
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.
Proposes Deep Fair Clustering for fair clustering with multiple protected groups.
problem Ensuring fair clustering with multiple protected groups.
method Deep Fair Clustering learns a fair cluster assignment function.
result Improves fairness while only slightly sacrificing clustering quality.
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.
Deep chest X-ray classifiers show bias in predicting diagnoses.
problem Bias in deep learning classifiers predicting diagnoses from chest X-rays.
method Trained convolutional neural networks on multiple public datasets to predict 14 diagnostic labels.
result True positive rates vary significantly among different protected attributes, indicating bias.
The paper analyzes how deep neural networks handle noisy labels and finds disparate impacts.
problem Disparate impacts of noisy labels on instances with different representation frequencies.
method Quantifying harms, analyzing solutions, and comparing their impacts on different frequency instances.
result Existing solutions lead to disparate treatments, benefiting higher-frequency instances more.
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.
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 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.
Paper tackles fairness in machine learning models by preventing representation disparity over time.
problem Representation disparity in machine learning models leading to unfairness over time.
method Develops a distributionally robust optimization (DRO) approach to minimize worst-case risk.
result Demonstrates that DRO prevents disparity amplification and improves minority group satisfaction.
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.
Study federates measurement of demographic disparities from quantile sketches.
problem Misalignment of fairness goals with siloed data collection and privacy regulations.
method Federated auditing of demographic parity through score distributions, using Wasserstein--Frechet variance and quantile summaries.
result Proposes a one-shot, communication-efficient protocol to estimate global disparity and its decomposition.
New method to quantify feature contributions to disparity without access to decision-making model.
problem Quantifying feature contributions to disparity when decision-making model is not accessible.
method Use information theory to measure redundant statistical dependency between protected attribute and feature.
result Quantify feature contributions to disparity using information theory.
Study reveals unique gender disparities in Bangladeshi TV advertisements and talk shows.
problem Gender disparity and skin color distribution in Bangladeshi TV content.
method Computer Vision, machine learning, head pose, gender detection, skin color estimation.
result Lighter skin tones are less prevalent than darker in Bangladeshi TV, contrary to popular perception.
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.
Proposes a method to quantify and decompose disparity in ML models, separating exempt and non-exempt components.
problem Quantifying disparity in ML models, especially when certain features are exempted due to their critical importance.
method Information-theoretic decomposition into exempt and non-exempt components, satisfying desirable properties.
result Proposes a measure of non-exempt disparity that satisfies all desirable properties, and shows impossibility results for observational measures.
Study reveals class disparities in balanced datasets through spectral imbalance.
problem Class disparities in balanced datasets are overlooked despite model performance gaps.
method Developed a theoretical framework and studied 11 encoders to diagnose spectral imbalance.
result Identified spectral imbalance as a source of class disparities in balanced datasets.
Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via co…
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.
Gradient descent works well for large NNs due to convexity in a transformed space.
problem Why gradient descent works well in non-convex NN optimization.
method Introduced canonical space and disparity matrix to prove convexity.
result Gradient descent converges to global minimum in large NNs.
Paper introduces xAUC metric to assess fairness of risk scores in bipartite ranking tasks.
problem Disparate impact of risk scores in non-binary, downstream uses.
method Investigates fairness in bipartite ranking tasks, introduces xAUC metric.
result xAUC metric reveals disparities not seen in binary classification performance.