Proposes a new fairness definition based on equity for machine learning classification.
problem Machine learning systems can perpetuate societal biases.
method Formalizes a new fairness definition based on equity, operationalizes it for classification, and evaluates its effectiveness.
result Demonstrates the effectiveness of the new fairness definition for equitable classification.
Clarifies the various fairness definitions in ML.
problem Addressing fairness in ML with different definitions.
method Analyzes and clarifies the differences between fairness definitions.
result Provides a clearer understanding of fairness definitions in ML.
This work introduces oblivious fairness definitions for image generation.
problem Fairness in image generation with uncertain sensitive attributes.
method Introduces oblivious fairness definitions and uses Posterior Sampling.
result Conditional Proportional Representation can be achieved obliviously.
Though there is a growing body of literature on fairness for supervised learning, the problem of incorporating fairness into unsupervised learning has been less well-studied. This paper studies fairness in the context of principal component analysis (PCA). We first present a definition of fairness for dimensionality re…
This work addresses building fair and calibrated models.
problem Building models that are both fair and calibrated.
method Developed a new definition of fairness and showed that group-wise calibration results in fairness. Proposed post-processing techniques and modifications of calibration losses.
result Demonstrated that ensuring group-wise calibration results in a fair model under the new definition of fairness.
The paper proposes a happiness-based fairness framework using linear programming.
problem Fairness in decision-making outcomes.
method Linear programming to compute optimal, fair post-processing strategies.
result Unified and extended fairness definitions with practical strengths across diverse scenarios.
Past literature has been effective in demonstrating ideological gaps in machine learning (ML) fairness definitions when considering their use in complex socio-technical systems. However, we go further to demonstrate that these definitions often misunderstand the legal concepts from which they purport to be inspired, an…
Algorithmic fairness, and in particular the fairness of scoring and classification algorithms, has become a topic of increasing social concern and has recently witnessed an explosion of research in theoretical computer science, machine learning, statistics, the social sciences, and law. Much of the literature considers…
Revises individual fairness by finding a fair metric for a model.
problem Difficulties in specifying a suitable fairness metric a priori.
method Introduces minimal metrics and applies randomized smoothing from adversarial robustness.
result Adapting minimal metrics to complex models yields interpretable fairness guarantees.
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…
Many machine learning systems make extensive use of large amounts of data regarding human behaviors. Several researchers have found various discriminatory practices related to the use of human-related machine learning systems, for example in the field of criminal justice, credit scoring and advertising. Fair machine le…
New fairness approach removes direct effects of unprivileged groups through causal regularization.
problem Ensuring fairness in machine learning models for unprivileged groups.
method Proposes a new fairness definition based on causal effects and develops regularizations to remove the impact of unprivileged groups on model outcomes.
result Demonstrates effectiveness of the approach on various datasets, reducing unfairness with minimal performance loss.
Paper proposes GEG to enhance fairness in binary and multi-class classification.
problem Fairness in multi-class classification tasks is under-explored.
method Formulates multi-objective problem between effectiveness and fairness constraints, proposes GEG algorithm.
result GEG improves fairness up to 92% and decreases accuracy up to 14%.
Extends ML fairness to handle minority groups over time.
problem Limitations of existing fairness criteria.
method Performative Distributionally Robust Optimization.
result Improves fairness for minority groups over time.
We consider the problem of how decision making can be fair when the underlying probabilistic model of the world is not known with certainty. We argue that recent notions of fairness in machine learning need to explicitly incorporate parameter uncertainty, hence we introduce the notion of {\em Bayesian fairness} as a su…
Paper introduces threshold invariant fairness to ensure equitable predictions across different groups.
problem Machine learning models can be unfair to certain groups based on sensitive attributes.
method Proposes threshold invariant fairness and uses two approximation methods to equalize risk distributions.
result Demonstrates effectiveness in alleviating threshold sensitivity in fairness models.
Proposes a framework for fairness in two-sided marketplaces.
problem Achieving fairness in two-sided marketplaces.
method Developed an end-to-end framework for fairness constraints from both sides of the marketplace, including dynamic aspects.
result Efficacy of the proposed framework demonstrated through simulations.
New framework for fairness in machine learning models using SHAP values and adversarial learning.
problem Fairness of model predictions, especially for unprivileged groups.
method Develops a new fairness definition and a framework using SHAP values and adversarial learning to mitigate bias.
result Models produced are fairer and performant, demonstrating the approach on various datasets.
New fairness concept extends minimax fairness to lexicographic fairness.
problem Fairness in supervised learning, especially lexicographic fairness.
method Introduced approximate lexifairness, derived algorithms for finding solutions, and proved generalization bounds.
result Proved that approximate lexifairness on training data implies approximate lexifairness on true distribution.
Fairness measures fail in predictive settings that intentionally shift outcomes.
problem Fairness measures fail in performative prediction settings.
method Formalized concept shift and counterfactual outcomes.
result Predictors that are fair during training become unfair during deployment.
We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens arising from the Humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions inclu…
In recent years, machine learning techniques have been increasingly applied in sensitive decision making processes, raising fairness concerns. Past research has shown that machine learning may reproduce and even exacerbate human bias due to biased training data or flawed model assumptions, and thus may lead to discrimi…
There has been much discussion recently about how fairness should be measured or enforced in classification. Individual Fairness [Dwork, Hardt, Pitassi, Reingold, Zemel, 2012], which requires that similar individuals be treated similarly, is a highly appealing definition as it gives strong guarantees on treatment of in…
Enhances fairness in predictions without sacrificing accuracy.
problem Balancing fairness and predictive performance in machine learning.
method Model ensemble-based post-processing framework.
result Framework effectively enhances fairness while maintaining predictive accuracy.
Two simple methods learn fair metrics from data to improve fairness in ML tasks.
problem Lack of widely accepted fair metrics for many ML tasks hinders individual fairness adoption.
method Presented two simple ways to learn fair metrics from various data types.
result Fair training with learned metrics improves fairness on three ML tasks.
Ensuring that classifiers are non-discriminatory or fair with respect to a sensitive feature (e.g., race or gender) is a topical problem. Progress in this task requires fixing a definition of fairness, and there have been several proposals in this regard over the past few years. Several of these, however, assume either…
Fair Adversarial Networks remove bias from data.
problem Bias in datasets leads to biased outcomes, making analysis illegal and sub-optimal.
method Remove bias from data by altering all proxy variables, ensuring fairness without changing analytical pipelines.
result Fair Adversarial Networks effectively remove bias from data.
Introduces principal fairness for fair decision-making.
problem Discrimination among similarly affected individuals.
method Uses principal stratification from causal inference.
result Explicitly accounts for decision impacts, not just protected attributes.
Abstract reviews mathematical fairness in machine learning.
problem Ensuring fairness in machine learning models.
method Independence-based approach to fairness definitions and methodologies.
result Optimal fair classifiers and predictors under equality of odds are derived.
Proposes a sequential framework for fairness in multiple sensitive attributes.
problem Fairness in the presence of multiple sensitive attributes.
method Sequential framework using multi-marginal Wasserstein barycenters.
result Closed-form solution for sequentially fair predictor.
New tools for assessing and correcting bias in AI algorithms.
problem Fairness and bias in AI algorithms, especially when ground truth data is unavailable.
method Three tools: controlled fairness, retraining algorithms, and parameter adjustment algorithms.
result Effective in reducing bias and improving fairness in AI models.
Algorithm ensures fair ranking by minority groups alongside majority groups.
problem Ensuring fair ranking of items from minority groups alongside majority groups.
method Optimal transport-based regularizer for individual fairness and efficient optimization algorithm.
result Certifiably individually fair LTR models are achieved.
We develop a theory which applies to any market dynamics that satisfy a fair market assumption on the nullity of the average profit of simple market making strategies. We show that for any such fair market, there exists a martingale fair price which corresponds to the average liquidation value (at the ask or the bid) o…
This work facilitates ensuring fairness of machine learning in the real world by decoupling fairness considerations in compound decisions. In particular, this work studies how fairness propagates through a compound decision-making processes, which we call a pipeline. Prior work in algorithmic fairness only focuses on f…
A recent trend of fair machine learning is to define fairness as causality-based notions which concern the causal connection between protected attributes and decisions. However, one common challenge of all causality-based fairness notions is identifiability, i.e., whether they can be uniquely measured from observationa…
Meta-theorems validate fair regression algorithms under demographic parity constraints.
problem Regression under demographic parity constraints.
method Meta-theorems and post-processing methods.
result Fair minimax optimal regression can be achieved through post-processing.
Proposes MFSWB for marginal fairness in SWB, improving efficiency and performance.
problem Achieving marginal fairness in SWB averaging.
method Defining MFSWB as a constrained SWB problem, proposing two surrogate problems and a new slicing distribution.
result Surrogate MFSWB problems effectively minimize distances to marginals and encourage marginal fairness.
New concept of within-group fairness improves AI fairness without sacrificing accuracy.
problem Fairness issues in AI models treating individuals in the same sensitive group unfairly.
method Introducing within-group fairness, proposing mathematical definitions, and developing learning algorithms.
result Improves within-group fairness without sacrificing accuracy and between-group fairness.
FairVIC improves fairness in neural networks without sacrificing accuracy.
problem Mitigating bias in automated decision-making systems, particularly in deep learning models.
method Integrates variance, invariance, and covariance terms into the loss function during training to abstract fairness concepts.
result Significant improvements in fairness across all tested metrics without compromising accuracy.
Machine fairness is impossible to achieve fully due to historical biases.
problem Machine learning models inherit biases from historical data, making it impossible to satisfy fairness metrics simultaneously.
method Presented a causal perspective to the impossibility theorem of fairness.
result It is impossible to satisfy fairness metrics like demographic parity, equal opportunity, and equalized odds simultaneously.
New algorithm improves group fairness in social classification problems by exploiting performativity.
problem Inequities in social classification problems due to performativity.
method Develops algorithmic fairness practices that leverage performativity to achieve stronger group fairness guarantees.
result Achieves stronger group fairness guarantees compared to non-performative settings.
Since many critical decisions impacting human lives are increasingly being made by algorithms, it is important to ensure that the treatment of individuals under such algorithms is demonstrably fair under reasonable notions of fairness. One compelling notion proposed in the literature is that of individual fairness (IF)…
New framework for fairness in continuous protected attributes.
problem Inherited biases in AI predictions with continuous protected attributes.
method Formalizes SP and PP through path-specific partial derivatives, introduces a fair tuning algorithm.
result Existence and construction of fair predictors that satisfy SP along not-allowed paths and PP along allowed paths.
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.
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.
This paper introduces efficient approximations for fairness criteria in regression models.
problem Measuring fairness in real-valued outcomes (regression settings) is computationally challenging.
method Fast approximations of mutual information for independence, separation, and sufficiency fairness criteria.
result The method achieves state-of-the-art accuracy/fairness tradeoffs in real-world datasets.
We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conceptual mapping, many existing definition of algorithmic fairness, such as predictive value parity and…
New model considers unfairness complaints to ensure multiple fairness criteria.
problem Ensuring fairness in systems that may conflict with each other.
method Data-driven model guided by unfairness complaints, supports multiple fairness criteria, and considers their incompatibilities. Stochastic and adversarial settings analyzed with efficient algorithms.
result Efficient algorithms for both stochastic and adversarial settings with competitive guarantees.