Study fairness in intervention to maximize outcomes.
problem Fairness in intervention on a given node.
method Counterfactual estimation with partial causal model knowledge.
result Theoretical guarantees on error probability and effectiveness of algorithm.
Framework achieves fairness in predictions using partially known causal graph over clusters of variables.
problem Achieving fairness in algorithmic decisions when causal graph knowledge is limited.
method Leverages a causal graph over clusters of variables to train a prediction model, reducing interventional distribution discrepancies.
result Framework strikes a better balance between fairness and accuracy than existing approaches under limited causal graph knowledge.
VACA models graph data for causal inference without hidden confounders.
problem Causal inference in observational data with hidden confounders.
method Variational graph autoencoders for structural causal models.
result Accurately approximates interventional and counterfactual distributions.
FairPrep aims to improve fairness in machine learning by providing best practices.
problem Lack of best practices in fairness-enhancing interventions.
method Developer-centered design and evaluation framework for fairness-enhancing interventions.
result Hyperparameter tuning and data cleaning methods impact fairness outcomes.
Most approaches in algorithmic fairness constrain machine learning methods so the resulting predictions satisfy one of several intuitive notions of fairness. While this may help private companies comply with non-discrimination laws or avoid negative publicity, we believe it is often too little, too late. By the time th…
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.
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…
Study suggests using information flow measures to target interventions in neural networks.
problem Identifying neural network edges that can be pruned to reduce bias.
method Used M-information flow framework to measure and compare information flows about true labels and protected attributes, and evaluated pruning effects on bias reduction. result Pruning edges with larger information flows about protected attributes reduces bias at the output.
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.
The study quantifies and compares aleatoric and epistemic discrimination in ML models.
problem Sources of discrimination in ML models and their impact on performance.
method Quantifying aleatoric and epistemic discrimination using statistical experiments and model accuracy.
result State-of-the-art fairness interventions are effective at removing epistemic discrimination but not aleatoric discrimination in datasets with missing values.
The wide spread usage of automated data-driven decision support systems has raised a lot of concerns regarding accountability and fairness of the employed models in the absence of human supervision. Existing fairness-aware approaches tackle fairness as a batch learning problem and aim at learning a fair model which can…
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.
Paper shows fairness and domain adaptation can work together.
problem Algorithmic bias and distributional shifts in ML models.
method Leveraging fairness and distribution shifts, the paper shows how domain adaptation methods can mitigate bias.
result Enforcing individual fairness can improve out-of-distribution accuracy under covariate shift.
The paper proposes Tier Balancing for dynamic fairness in decision-making.
problem Achieving long-term fairness in decision-making processes.
method Causal modeling with DAGs to investigate dynamic fairness.
result Tier Balancing is a more natural approach to achieve long-term fairness, capturing latent causal factors.
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.
New approach to counterfactual reasoning avoids demographic interventions.
problem Limitations of traditional counterfactual reasoning in AI systems.
method Backtracking counterfactual approach instead of interventional.
result Allows addressing social concerns without demographic interventions.
A new decision tree method tackles fairness in datasets with missing values.
problem Fairness concerns in machine learning models trained on data with missing values.
method An integrated approach based on decision trees that incorporates missing values directly and optimizes a fairness-regularized objective function.
result Our method outperforms existing fairness intervention methods applied to imputed datasets.
With the aim of building machine learning systems that incorporate standards of fairness and accountability, we explore explicit subgroup sample complexity bounds. The work is motivated by the observation that classifier predictions for real world datasets often demonstrate drastically different metrics, such as accura…
In many application areas---lending, education, and online recommenders, for example---fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both immediate and long-term effects for individuals and demographic groups. We discuss causal directed a…
New approach to explain fairness in machine learning models.
problem Detect, understand, and mitigate unfairness in machine learning models.
method Shapley value paradigm and meta algorithm for training-time fairness interventions.
result Meta algorithm provides insight into accuracy-fairness trade-off.
The paper proposes a method to measure fairness through equality of effort using algorithmic recourse.
problem Measuring fairness through equality of effort in automated systems.
method Applying algorithmic recourse to quantify equality of effort, overcoming previous limitations.
result An algorithm for assessing equality of effort has been developed and validated.
The paper proposes a method to improve fairness in machine learning models without refitting.
problem Mitigating biases in machine learning models that disadvantage certain groups.
method Infinitesimal jackknife-based approach to drop selected training data points.
result The intervention improves fairness without significantly reducing predictive performance.
New datasets improve fairness research by revealing UCI Adult's limitations.
problem Limitations of UCI Adult dataset in fairness research.
method Reconstructed a superset of UCI Adult data from US Census sources.
result New datasets reveal trade-offs between fairness criteria and performance.
Proposes a method to enforce fairness in machine learning models without sensitive data.
problem Bias in machine learning models from historical data.
method Infers sensitive attributes from auxiliary features and integrates fairness constraints into model training.
result Mitigates bias while preserving predictive accuracy.
New method uses causal thinking to make AI fairer decisions.
problem Designing fair machine learning models that treat equal individuals equally and unequals unequally.
method Rank-preserving interventional distributions and warping method.
result Warping method effectively identifies discriminated individuals and mitigates unfairness.
We introduce the BriarPatch, a pixel-space intervention that obscures sensitive attributes from representations encoded in pre-trained classifiers. The patches encourage internal model representations not to encode sensitive information, which has the effect of pushing downstream predictors towards exhibiting demograph…
The persistence of racial inequality in the U.S. labor market against a general backdrop of formal equality of opportunity is a troubling phenomenon that has significant ramifications on the design of hiring policies. In this paper, we show that current group disparate outcomes may be immovable even when hiring decisio…
Algorithm simulates counterfactuals for fairness analysis.
problem Analytical intractability of counterfactuals in conditional distributions.
method Proposes an algorithm using particle filtering for discrete and continuous variables.
result Asymptotically valid inference for counterfactuals.
DFL framework improves action and outcome fairness in policy learning.
problem Fairness in policy learning, especially action and outcome fairness.
method Integrates action and outcome fairness into a multi-objective optimization problem using a lexicographic weighted Tchebyshev method.
result DFL framework improves both action and outcome fairness with minimal value reduction.
Study finds incorporating fairness in healthcare models doesn't improve performance or net benefit.
problem Addressing health inequities in healthcare through algorithmic fairness.
method Empirical case study using models to estimate atherosclerotic cardiovascular disease risk.
result Incorporating fairness considerations into model training objective does not improve model performance or net benefit.
Two new methods assess feature importance for fairness in machine learning models.
problem Understanding how features influence fairness in machine learning models.
method Two model-agnostic approaches: permutation and occlusion.
result Simple, scalable, and interpretable methods to quantify feature importance for fairness.
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.
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.
New framework enforces demographic parity on distribution tails.
problem Enforcing demographic parity on entire distribution can degrade accuracy.
method Optimal transport theory, focusing on distribution tails.
result More nuanced and context-sensitive fairness interventions.
Benchmark assesses fairness in algorithmic uncertainty, revealing consistent and calibrated estimates improve fairness.
problem Challenges in managing uncertainty in fairness evaluations for predictive algorithms.
method Introduces FairlyUncertain, an axiomatic benchmark for evaluating uncertainty in fairness.
result Consistent and calibrated uncertainty estimates improve fairness without explicit fairness interventions.
Personalized models using group attributes reduce performance, study finds.
problem Reducing performance of models using group attributes like race or gender.
method Formal conditions and collective preference guarantees to ensure fair use.
result Models personalized with group attributes reduce performance at a group level.
Methodology explores fairness limits in decision tree classifiers.
problem Understanding statistical limits of bias mitigation in machine learning.
method Multi-objective framework optimizing accuracy and fairness.
result Decision tree models can be optimized for fairness with minimal accuracy loss.
New metric reduces arbitrariness in fair binary classification predictions.
problem Variance in predictions leads to arbitrary decisions in fair classification.
method Developed a self-consistency metric and an abstention algorithm.
result Fair binary classification is often close to fair due to variance, not interventions.
FairPOT balances fairness and AUC performance by selectively transforming risk scores.
problem Balancing fairness and AUC performance in high-stakes domains.
method FairPOT uses proportional optimal transport to selectively transform risk scores.
result FairPOT consistently improves fairness with minimal AUC degradation or even positive gains.
Personalized interventions in social services, education, and healthcare leverage individual-level causal effect predictions in order to give the best treatment to each individual or to prioritize program interventions for the individuals most likely to benefit. While the sensitivity of these domains compels us to eval…
New research shows fairness in machine learning can sometimes make disadvantaged groups worse off.
problem The impact of fairness constraints in machine learning on different groups.
method Unified, population-level (Bayes) framework for binary classification under prevalent group fairness notions.
result Fairness in machine learning can lead to leveling down, making one or both groups worse off.
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.
This research tackles group fairness in predictive process monitoring by ensuring predictions are independent of sensitive group membership.
problem Predictive models using biased historical data can perpetuate unfair behavior in new cases.
method Investigates independence through metrics like ΔDP and a composite loss function balancing predictive performance and fairness.
result Proposes and validates a composite loss function for training models that balance fairness and performance.
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.
How do we learn from biased data? Historical datasets often reflect historical prejudices; sensitive or protected attributes may affect the observed treatments and outcomes. Classification algorithms tasked with predicting outcomes accurately from these datasets tend to replicate these biases. We advocate a causal mode…
FAE framework tackles fairness in machine learning by balancing data and adjusting decision boundaries.
problem Discrimination in automated decision-making based on machine learning algorithms.
method Combines pre- and post-processing fairness interventions to address group imbalance, class imbalance, and class overlap.
result Improves fairness in machine learning models by balancing data and adjusting decision boundaries.
The paper reconciles two conflicting fairness criteria in algorithmic risk scores.
problem How to reconcile calibration and equal error rates in algorithmic risk scores.
method Derive necessary and sufficient conditions for existence of calibrated scores achieving equal error rates, then present an algorithm to find the most accurate score subject to both criteria.
result The method can eliminate error disparities while maintaining calibration and improve profit in credit lending.
We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is conditionally independent of group membership given the score. We show that under r…