Paper defines and solves a problem in representation learning to ensure fairness with high confidence.
problem Learning fair representations with high confidence guarantees for all downstream tasks.
method Formally defines the problem, introduces FRG framework, proves high probability fairness, and demonstrates effectiveness empirically.
result FRG framework provides high-confidence guarantees for limiting unfairness across all downstream models and tasks.
This work proposes a new pre-processing method for supervised learning to improve fairness without sacrificing utility.
problem Improving fairness in supervised learning without compromising model performance.
method Task-tailored pre-processing approach that balances fairness and utility.
result The proposed method preserves consistent trade-offs among multiple downstream models and improves fairness in computer vision tasks.
Introduces lookahead counterfactual fairness to account for downstream effects of ML predictions.
problem Downstream effects of ML predictions on individuals not considered by counterfactual fairness.
method Introduces lookahead counterfactual fairness (LCF), a new fairness notion that considers future status. Proposes an algorithm based on theoretical conditions.
result Proposes an algorithm to achieve lookahead counterfactual fairness and validates it on synthetic and real data.
FWC creates fair synthetic samples for machine learning tasks.
problem Addressing biases in machine learning models for fair decision-making.
method FWC uses an efficient majority minimization algorithm to minimize Wasserstein distance while enforcing demographic parity.
result FWC achieves a competitive fairness-utility tradeoff and reduces biases in predictions from large language models.
Proposes FairRR to improve fairness in machine learning models through randomized response.
problem Achieving group fairness in machine learning models.
method Formulates group fairness as optimizing a design matrix in Randomized Response, proposing FairRR.
result Demonstrates FairRR yields excellent model utility and fairness.
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.
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.
DECAF generates fair synthetic data by embedding causal relationships.
problem Generating fair synthetic data from biased training data.
method DECAF uses a GAN with a structural causal model to embed causal relationships and debias synthetic data.
result DECAF successfully removes bias and generates high-quality synthetic data.
The paper tackles fair representation learning by smoothing feature mappings.
problem Legal liability for discriminatory use of data by organizations.
method Mapping features to a fair representation space, certifying fairness through chi-squared mutual information.
result Smoothing representation distribution provides generalization guarantees of fairness and maintains accuracy for downstream tasks.
New method certifies individual fairness in representations.
problem Ensuring fairness in data representations without sacrificing utility.
method Mapping similar individuals to close latent representations to certify individual fairness.
result Certifies individual fairness for existing and new data points.
The paper explores fair clustering, a niche area in machine learning.
problem Fairness in clustering remains underexplored despite its importance.
method Assesses existing work and proposes new directions for fair clustering.
result Widening normative principles and knowledge of downstream processes can enhance fair clustering research.
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.
Paper creates fair synthetic data ensuring equal predictions across sensitive attributes.
problem Ensuring fair predictions across sensitive attributes in synthetic data.
method Equalizing target probability distributions across sensitive attributes in synthetic data generation.
result Synthetic data provides strong fair predictions, equal across all thresholds.
Private release of sensitive data enables fair learning.
problem Learning fair predictors with restricted sensitive data.
method Private release of sensitive demographic data, adapting non-discriminatory learners.
result The approach provides theoretical guarantees on performance for fair predictors.
New method learns fair representations by separating out protected attributes.
problem Learning fair representations invariant to protected attributes.
method FD-VAE: disentangles latent space into target, protected, and mutual attributes.
result FD-VAE outperforms previous methods in fairness metrics.
New method controls bias in training data for fair outcomes.
problem Ensuring equal treatment between different groups in machine learning.
method Contrastive information estimation to control mutual information between representations and protected attributes.
result Our method provides strong theoretical guarantees on the parity of any downstream algorithm.
A new method for fair classification using characteristic function distance.
problem Fairness in high-stakes decision-making with sensitive groups.
method Proposes a novel approach based on characteristic function distance to ensure minimal sensitive information in learned representations.
result Consistently matches or achieves better fairness and predictive accuracy than existing methods.
Recently there has been a significant interest in learning disentangled representations, as they promise increased interpretability, generalization to unseen scenarios and faster learning on downstream tasks. In this paper, we investigate the usefulness of different notions of disentanglement for improving the fairness…
We present a data-driven framework for learning fair universal representations (FUR) that guarantee statistical fairness for any learning task that may not be known a priori. Our framework leverages recent advances in adversarial learning to allow a data holder to learn representations in which a set of sensitive attri…
Study shows disentanglement models learn correlations from data, impacting fairness.
problem Disentanglement models learn correlations in real-world data, affecting downstream applications.
method Empirical study on 4260 models, analyzing correlations in latent representations.
result Systematically induced correlations are learned by disentanglement models, impacting fairness.
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those…
Bayesian data selection framework ensures fairness in machine learning models.
problem High computational costs and limited scalability of fairness-aware methods.
method Bayesian data selection framework using generalized discrepancy measures.
result Consistently outperforms existing methods in fairness and accuracy.
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.
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.
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.
FATE framework attacks graph learning models to amplify bias deceptively.
problem Achieving poisoning attacks on graph learning models to exacerbate bias deceptively.
method Bi-level optimization problem and meta learning-based framework named FATE.
result FATE amplifies bias of graph neural networks while maintaining downstream task utility.
Algorithm learns similarity metrics for individual fairness.
problem Difficulty in learning similarity metrics for individual fairness.
method Gradient descent and Bradley-Terry model for pairwise comparisons.
result Algorithm converges to ground truth metric for individual fairness.
Community-based system dynamics improves ML fairness by involving excluded stakeholders.
problem Bias in ML system development during problem formulation.
method Community-based system dynamics (CBSD) for stakeholder participation.
result CBSD facilitates deeper problem understanding and bias mitigation.
Integrates fairness guarantees into deep learning models.
problem Ensuring fairness in deep learning models.
method Integrates a differentiable fairness layer into neural models and uses an online primal-dual algorithm for provable fairness guarantees.
result Guarantees a chosen notion of output parity in deep learning models.
We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives. We train a reinforcement learning agent to sequentially acquire a subset of the information while balancing accuracy and fairness …
People are rated and ranked, towards algorithmic decision making in an increasing number of applications, typically based on machine learning. Research on how to incorporate fairness into such tasks has prevalently pursued the paradigm of group fairness: giving adequate success rates to specifically protected groups. I…
It has been shown that dimension reduction methods such as PCA may be inherently prone to unfairness and treat data from different sensitive groups such as race, color, sex, etc., unfairly. In pursuit of fairness-enhancing dimensionality reduction, using the notion of Pareto optimality, we propose an adaptive first-ord…
The paper explores fairness, welfare, and equity in personalized pricing across various applications.
problem Interplay of fairness, welfare, and equity in personalized pricing based on customer features.
method Comprehensive literature review and observational metrics without underlying valuation distribution assumptions.
result Personalized pricing can expand access, improve welfare, and increase revenue or budget utilization.
UBM transfers bias mitigation from upstream to downstream tasks efficiently.
problem Bias in fine-tuned language models across various tasks.
method Apply bias mitigation to an upstream model, then fine-tune a downstream model on this mitigated model.
result UBM effects transfer to new downstream tasks, creating less biased models.
Multiverse analysis helps prevent fairness hacking and evaluate model design decisions.
problem Downstream effects of ADM systems depend on implicit design and evaluation decisions.
method Turn implicit decisions into explicit ones, create a grid of decision combinations, compute fairness and performance metrics.
result Decisions regarding evaluation can lead to vastly different fairness metrics for the same model.
MAPPING debiases GNNs for fair node classification with limited leakage.
problem Graph Neural Networks inherit and exacerbate historical discrimination in high-stake domains.
method MAPPING uses distance covariance-based fairness constraints and adversarial debiasing.
result MAPPING achieves better trade-offs between fairness and utility, mitigating privacy risks.
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.
Study optimal and equitable encouragement policies for treatment adherence.
problem Optimal treatment adherence policies in the presence of human non-adherence.
method Covariate-conditional no-direct-effect model of encouragement; tractable policy characterizations under constraints.
result Induced treatment take-up is the fairness target, not recommendation rates.
Framework generates fair synthetic data to avoid biases.
problem Societal and historic biases in training data lead to biased algorithms.
method Self-supervised learning with fairness constraints.
result Generated fair synthetic data maintains relationships while controlling biases.
Study examines biases in clinical word embeddings, revealing performance gaps across groups.
problem Biases in clinical word embeddings leading to performance differences across groups.
method Pretrained BERT models on MIMIC-III, fill-in-the-blank method, fairness evaluation on clinical tasks.
result Classifiers trained from BERT representations exhibit statistically significant differences in performance across groups.
MCRAGE generates synthetic data to balance healthcare datasets.
problem Imbalanced datasets in healthcare lead to biased model performance for minority groups.
method Generative modeling to create synthetic data for underrepresented classes.
result MCRAGE improves model performance on minority groups.
As algorithmic prediction systems have become widespread, fears that these systems may inadvertently discriminate against members of underrepresented populations have grown. With the goal of understanding fundamental principles that underpin the growing number of approaches to mitigating algorithmic discrimination, we …
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…
In many machine learning applications, there are multiple decision-makers involved, both automated and human. The interaction between these agents often goes unaddressed in algorithmic development. In this work, we explore a simple version of this interaction with a two-stage framework containing an automated model and…
Where machine-learned predictive risk scores inform high-stakes decisions, such as bail and sentencing in criminal justice, fairness has been a serious concern. Recent work has characterized the disparate impact that such risk scores can have when used for a binary classification task. This may not account, however, fo…
This work addresses fairness in ML models by training and evaluating attribute classifiers under uncertain and incomplete data.
problem Challenges in fairness metrics due to uncertain and incomplete data.
method Developed a theoretical and empirical analysis to understand and improve bias estimation in the data-scarce regime.
result The test accuracy of the attribute classifier is not always correlated with its effectiveness in bias estimation.
Data containing human or social attributes may over- or under-represent groups with respect to salient social attributes such as gender or race, which can lead to biases in downstream applications. This paper presents an algorithmic framework that can be used as a data preprocessing method towards mitigating such bias.…
New method generates synthetic survival data by conditioning on event times and censoring indicators.
problem Generating accurate synthetic survival data with censored event times.
method Conditioning covariates on event times and censoring indicators using existing tabular data generation models.
result Our method consistently outperforms baselines and improves survival model performance.