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.
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.
New framework for fair online allocation in continuous time with deadlines.
problem Fair allocation under deadlines in continuous-time online learning.
method Continuous-time utility maximization, dual ascent optimization for time averages.
result Achieves ildeO(B−1/2) regret bound in the absence of statistical knowledge. Machine learning (ML) can automate decision-making by learning to predict decisions from historical data. However, these predictors may inherit discriminatory policies from past decisions and reproduce unfair decisions. In this paper, we propose two algorithms that adjust fitted ML predictors to make them fair. We focu…
The excessive compensation packages of CEOs of U.S. corporations in recent years have brought to the foreground the issue of fairness in economics. The conventional wisdom is that the free market for labor, which determines the pay packages, cares only about efficiency and not fairness. We present an alternative theory…
The paper critiques ε-fairness, showing it can lead to unfair outcomes and proposes a utility-based approach.
problem The limitations of probabilistic fairness metrics in real-world contexts.
method Utility-based approach to measure fairness, addressing the issue of unavailable data on false negatives.
result A utility-based approach uncovers necessary actions to achieve true fairness, contrasting with traditional probability-based evaluations.
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.
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…
New causal approach resolves fairness and accuracy trade-offs.
problem Fairness and predictive performance are often at odds.
method Causal pre-processing methods to approximate the FiND world.
result Pre-processing resolves both fairness and accuracy trade-offs.
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.
This paper critiques machine learning fairness from a consequentialist perspective.
problem The ethical foundations of fairness in machine learning.
method Consequentialist analysis of existing fairness definitions and machine learning perspectives.
result Consequentialism highlights ethical tradeoffs in fairness definitions and decision making.
Machine learning based decision making systems are increasingly affecting humans. An individual can suffer an undesirable outcome under such decision making systems (e.g. denied credit) irrespective of whether the decision is fair or accurate. Individual recourse pertains to the problem of providing an actionable set o…
New algorithm for bandits with delayed action effects, reducing regret.
problem Delayed impact of actions in multi-armed bandits.
method Formulated a new bandit setting with delayed action effects, proposed an algorithm with regret bound.
result Achieved a regret of ildeO(KT2/3) and showed a matching lower bound. 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.
Introduces privilege scores to measure and interpret protected attribute-related privilege in machine learning models.
problem Lack of explicit formulation of non-neutrality in fairness-aware machine learning methods.
method Privilege scores (PS) and privilege score contributions (PSCs) to measure and interpret protected attribute-related privilege.
result Demonstrates the broad applicability of PS and PSCs in gender and racial privilege in mortgage and college admissions applications.
The paper tackles fair sequential decision making with biased linear bandit feedback.
problem Fair sequential decision making with biased linear bandit feedback.
method Phased elimination algorithm to correct unfair evaluations, establishing upper bounds on regret.
result The worst-case regret is smaller than O(κ∗1/3log(T)1/3T2/3). The paper shows how to use proxy attributes for fairness in machine learning models with missing sensitive group data.
problem Measuring and enforcing fairness in machine learning models with incomplete sensitive group data.
method Using proxy-sensitive attributes to derive upper bounds on multiaccuracy and multicalibration violations and adjust models to satisfy these fairness notions.
result Provable upper bounds on multiaccuracy and multicalibration violations can be derived using proxy-sensitive attributes in the absence of sensitive group data.
Unified approach to fair online learning with stochastic contexts.
problem Fairness in online learning with unknown sensitive contexts.
method Adapting Blackwell's approachability theory to handle unknown contexts' distributions.
result Characterization of optimal trade-off between fairness and performance objectives.
Improves global counterfactual explanations for model recourse.
problem Inability to provide explanations beyond local instances.
method Investigates and improves Actionable Recourse Summaries (AReS) for global counterfactual explanations.
result Develops more efficient and interactive explainability tools.
New algorithm for fair ranking in contextual bandits with concave rewards.
problem Fair ranking in recommendation systems.
method Geometric interpretation of CBCR as optimization, Frank-Wolfe analyses.
result First algorithm with provably vanishing regret for CBCR.
Recent attempts to achieve fairness in predictive models focus on the balance between fairness and accuracy. In sensitive applications such as healthcare or criminal justice, this trade-off is often undesirable as any increase in prediction error could have devastating consequences. In this work, we argue that the fair…
Simple greedy algorithms can excel in multi-objective bandits with multiple good arms.
problem Optimizing multiple objectives in bandits is traditionally harder.
method Introduced greedy algorithms that exploit multiple good arms for multiple objectives.
result Simple greedy algorithms achieve strong performance in multi-objective bandits.
Decomposes bias in linear models under demographic parity constraints.
problem Understanding and quantifying bias in linear models under fairness constraints.
method Post-processing framework to decompose bias into direct and indirect components.
result Analytical characterization of how demographic parity reshapes model coefficients.
The study of fairness in intelligent decision systems has mostly ignored long-term influence on the underlying population. Yet fairness considerations (e.g. affirmative action) have often the implicit goal of achieving balance among groups within the population. The most basic notion of balance is eventual equality bet…
Today, artificial intelligence systems driven by machine learning algorithms can be in a position to take important, and sometimes legally binding, decisions about our everyday lives. In many cases, however, these systems and their actions are neither regulated nor certified. To help counter the potential harm that suc…
FST.ai 2.0 improves Taekwondo decision-making with AI, reducing review time and increasing trust.
problem Fair, transparent, and explainable decision-making in Taekwondo.
method Pose-based action recognition, epistemic uncertainty modeling, interactive dashboards.
result 85% reduction in decision review time, 93% referee trust in AI-assisted decisions.
Algorithmic risk assessments are increasingly used to help humans make decisions in high-stakes settings, such as medicine, criminal justice and education. In each of these cases, the purpose of the risk assessment tool is to inform actions, such as medical treatments or release conditions, often with the aim of reduci…
Machine learning is becoming an ever present part in our lives as many decisions, e.g. to lend a credit, are no longer made by humans but by machine learning algorithms. However those decisions are often unfair and discriminating individuals belonging to protected groups based on race or gender. With the recent General…
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.
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.
A new fairness metric for decision-making algorithms, conditioning on known fair variables.
problem Fairness issues in decision-making systems.
method Conditional fairness metric, Derivable Conditional Fairness Regularizer (DCFR), adversarial representation.
result Traditional fairness notations are special cases of the new conditional fairness notation.
Fair Mixup improves fairness in classifiers by interpolating between groups.
problem Ensuring fairness in classifiers during training and evaluation.
method Fair Mixup uses interpolation of samples between groups to enforce fairness constraints.
result Fair Mixup ensures better generalization of fairness in various benchmarks.
Paper proposes a modified fairness constraint to address shortcomings of counterfactual fairness.
problem Counterfactual fairness is not a necessary condition for algorithmic fairness.
method Analyzed hypothetical scenario and explicated discrimination to develop causal relevance fairness.
result Causal relevance fairness is a modified constraint that circumvents shortcomings of counterfactual fairness.
CST detects discrimination by comparing protected and non-protected individuals with a counterfactual.
problem Detecting discrimination in classifiers using legal fairness conditions.
method Operationalizes fairness given the difference using counterfactual reasoning.
result CST uncovers more discrimination cases than traditional situation testing.
The paper connects counterfactual fairness to robust prediction and group fairness using causal context.
problem The challenge of ensuring fairness in AI systems when counterfactuals cannot be directly observed.
method Using causal context to bridge counterfactual fairness, robust prediction, and group fairness.
result Counterfactual fairness is equivalent to group fairness metrics in specific contexts.
New fairness notion helps identify fair auditors for evaluating decision-support systems.
problem Identifying fair auditors to evaluate decision-support systems for bias.
method Introducing a non-comparative fairness notion based on desired system properties.
result The proposed fairness notion provides guarantees in terms of comparative fairness.
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.
New machine learning paradigm ignores loss function until action time.
problem Learning with unknown loss functions.
method Introduces omnipredictors for any loss function.
result Extracts predictive power from any class, ignoring loss function.
FCA improves fair clustering by optimizing utility and fairness.
problem Balancing fairness and utility in clustering.
method FCA alternates between aligning data and optimizing cluster centers in an aligned space.
result FCA achieves a superior trade-off between fairness and utility.
Fair MP-Boost improves fairness and interpretability in boosting methods.
problem Improving fairness and interpretability in boosting methods.
method Fair MP-Boost uses adaptive sampling of minipatches to balance accuracy and fairness.
result Fair MP-Boost enhances fairness and accuracy while providing interpretable feature importance.
New framework for fair ranking with noisy protected attributes.
problem Errors in socially-salient attributes undermine fairness guarantees.
method Modeling perturbations in protected attributes and incorporating probabilistic information.
result Framework provides provable guarantees on fairness and utility.
How can we build recommender systems to take into account fairness? Real-world recommender systems are often composed of multiple models, built by multiple teams. However, most research on fairness focuses on improving fairness in a single model. Further, recent research on classification fairness has shown that combin…
Algorithm samples fair rankings to ensure individual fairness while maintaining group fairness.
problem Fair ranking tasks with group fairness constraints and uncertainty in item utilities.
method Efficient algorithm that samples rankings from an individually-fair distribution ensuring group fairness.
result Expected utility of output ranking is at least α times optimal fair solution, where α depends on utilities and constraints.
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.
The paper explores fairness in credit scoring using machine learning.
problem The lack of research on fair machine learning in credit scoring.
method Revisits statistical fairness criteria, catalogs algorithmic options, and empirically compares fairness processors.
result Multiple fairness criteria can be approximately satisfied at once, and fair processors deliver a good balance between profit and fairness.
Proposes FACT, a diagnostic for understanding group fairness trade-offs.
problem Group fairness notions often conflict with each other, requiring a cost in model performance.
method Characterizes trade-offs via the fairness-confusion tensor and optimizes accuracy and fairness objectives.
result Demonstrates the use of FACT on synthetic and real datasets to understand accuracy-fairness trade-offs.
Proposes individual fairness for clustering, making data points prefer their own cluster.
problem No fair clustering for clustering data points.
method Introduces a new fairness notion for clustering and studies its feasibility and heuristics.
result Individual fairness for clustering is NP-hard in general but feasible for one-dimensional data.
Unified approach for fair classification with overlapping groups.
problem Ensuring fairness across multiple overlapping groups in prediction problems.
method Probabilistic population analysis leading to Bayes-optimal classifier, unifying existing methods.
result Outperforms baselines in fairness-performance tradeoff on real datasets.