New study shows fairness adjustments can perpetuate bias in machine learning.
problem Systematic censoring of training data by biased policies leads to residual unfairness in fair machine learning.
method Theoretical analysis and sample reweighting to estimate and adjust fairness metrics.
result Fairness-adjusted classifiers can perpetuate injustices against the same groups as the original data.
Graphical interpretation of unfairness in causal Bayesian networks.
problem Unfairness in datasets and models.
method Causal Bayesian networks to interpret and measure unfairness.
result Causal Bayesian networks provide a tool to measure and design fair models.
Unified approach to measure algorithmic unfairness using inequality indices.
problem Measuring and comparing fairness of algorithmic decision-making.
method Using inequality indices from economics to quantify unfairness at individual and group levels.
result Decomposes overall unfairness into between-group and within-group components, revealing tradeoffs.
New ML fairness measure excludes subjective opinions.
problem Lack of adaptation of ML models to specific applications.
method Formalised new notion of unfairness, quantified and visualised.
result Insights into ML systems' functioning to mitigate unfairness.
Develops tools to audit ML models for bias and unfairness.
problem Auditing ML models for individual bias and unfairness.
method Formalizes the task as an optimization problem and develops inferential tools for the optimal value.
result Demonstrates the utility of tools in revealing biases in COMPAS recidivism prediction instrument.
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 fairness metrics improve collaborative filtering fairness.
problem Collaborative filtering's bias in historical data leads to unfair predictions for minority groups.
method Identified and proposed four new fairness metrics to address different forms of unfairness.
result Our new metrics better measure fairness than baseline metrics and effectively reduce unfairness.
Proposes a fair classification model using robust optimization.
problem Preventing discrimination in classification models.
method Distributionally robust logistic regression with Wasserstein ball and convex unfairness measure.
result Improves fairness with minimal loss in predictive accuracy.
Optimal exit strategies of CPT gamblers in unfair gambles
problem Optimal exit strategies of gamblers with CPT preferences in games with strictly negative expected payoffs
method Formulating the problem as an optimal stopping problem on asymmetric random walks, applying geometric transformation, randomized strategies, and changing the decision variable
result The unfair problem in the infinite time horizon has finite values for a wide range of CPT parameter specifications
Paper compares fairness measures and feature importance measures using SHAP.
problem Comparing fairness measures and feature importance measures.
method Focus on SHAP, a game-theoretic measure of feature importance.
result Results for unfairness-prone datasets.
New method reduces unfairness in binary classification.
problem Achieving similar false positive and negative rates across two populations.
method Penalizes unfairness to achieve balanced false positive and negative rates.
result Empirically validated approach improves fairness and accuracy.
The paper tackles multi-level fairness in algorithmic systems, addressing bias at both individual and structural levels.
problem Algorithmic systems can unfairly impact marginalized groups, especially when considering only individual-level bias.
method Formalizes multi-level fairness using causal inference tools, addressing effects of sensitive attributes at multiple levels.
result Illustrates the importance of accounting for macro-level sensitive attributes in fairness assessments.
Advocates focusing on utility functions to avoid unfair outcomes.
problem Unfair outcomes from fairness criteria in optimizing policies.
method Defines value of information fairness and proposes modifying utility functions.
result Value of information fairness leads to better answers than existing fairness notions.
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 uncovers how model and data biases interact to cause unfairness in fraud detection.
problem Unfairness in fraud detection algorithms due to model and data biases.
method Taxonomy of data bias, hypotheses on fairness-accuracy trade-offs, real-world fraud use case study.
result Data bias affects fairness in expected value and variance, and simple pre-processing can balance group-wise error rates.
Framework improves fairness in machine learning models using adversarial techniques.
problem Unfair decision processes in machine learning models.
method Two-step framework involving fairness optimization and evasion attacks.
result Framework significantly improves fairness metrics on tested datasets.
New method detects and prevents unfairness in few-shot regression models.
problem Fairness issues in supervised few-shot meta-learning models.
method Causal Bayesian knowledge graph for dependency visualization, risk difference quantification, and fast-adapted bias-control approach.
result Efficiently detects and mitigates unfairness in model predictions.
The paper explores fair predictors in supervised learning using IPMs and Kolmogorov distance.
problem Achieving fairness in supervised learning with significant demographic effects.
method Identifying conditions for SP-fair predictors and using IPMs to measure unfairness.
result Fair predictors can improve accuracy and are computationally efficient.
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.
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.
FPFL mitigates unfairness in private federated learning.
problem Differential privacy degrades model performance on under-represented groups.
method Extends modified method of differential multipliers to private federated learning.
result FPFL reduces unfairness in trained models on private federated learning.
Formulates LGFO to measure fair ML systems using legal signals.
problem Formally incompatible measures of unfairness in ML systems.
method Uses legal signals to measure social cost of unfairness.
result LGFO aligns with societal view of unfairness.
Local discovery method uncovers direct unfairness in complex systems.
problem Identifying causal pathways of unfairness in complex domains.
method Local discovery for direct discrimination (LD3) method.
result LD3 returns a valid adjustment set (VAS) for assessing unfairness.
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.
This paper examines AI and ML bias and fairness issues.
problem Bias and unfairness in AI and ML algorithms.
method Overview of bias and fairness issues, types and sources of data bias, algorithmic unfairness, fairness metrics, and de-biasing techniques.
result Discussion of the limitations of fairness metrics and de-biasing techniques.
Proposes a method to learn fair classifiers without restrictive assumptions.
problem Fairness in machine learning decisions for individuals.
method Defines PIU and optimizes to control its upper bound.
result Guarantees fairness for each individual without restrictive assumptions.
Paper tackles unfair advantages in DARTS, presenting Fair DARTS to improve neural architecture search.
problem Performance collapse in DARTS due to unfair advantages in skip connections.
method Relax exclusive competition to collaborative, let architectural weights be independent, and use zero-one loss for discretization.
result New state-of-the-art results on CIFAR-10 and ImageNet, demonstrating the effectiveness of Fair DARTS.
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.
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.
Doubly fair dynamic pricing ensures equal prices for different groups over time.
problem Achieving equal prices for different groups in online dynamic pricing.
method Online learning algorithm that balances procedural and substantive fairness.
result Achieves i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret, zero procedural unfairness, and i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) substantive unfairness. New method detects and mitigates historical bias in data.
problem Detecting and explaining historical bias in data.
method Developed a sample bias criterion and algorithms to measure and counter sample bias.
result Derived bias score provides sample-level attribution and explanation of historical bias.
Paper tackles fairness in automated decision-making systems.
problem Fairness issues in automated decision-making systems.
method Introduces disparate mistreatment, a new measure of unfairness, and proposes convex-concave constraints for decision boundary-based classifiers.
result Effective at avoiding disparate mistreatment without significant accuracy loss.
Fairwashing occurs when machine learning models are made to appear fair through rationalization.
problem Rationalizing unfair black-box models to appear fair.
method LaundryML uses a regularized rule list enumeration algorithm to find fair rule lists approximating an unfair model.
result It is possible to systematically rationalize decisions from unfair black-box models using model and outcome explanations.
Fair decision-making method avoids ignoring fair pathways.
problem Learning fair decision systems in complex scenarios with sensitive attributes.
method Causal approach to disregard unfair pathways, corrects affected observations, uses for decision-making.
result Avoids ignoring fair information, widely applicable to complex scenarios.
This paper examines unfair trading practices in NFT markets.
problem Sophisticated actors exploit market inefficiencies for unfair profits.
method Analyzes three types of opportunistic trading strategies.
result Identifies and categorizes unfair trading practices in NFT markets.
New clustering method considers causal fairness to avoid bias.
problem Clustering algorithms can unintentionally propagate unfair disparities.
method Integrates causal fairness metrics into clustering algorithms.
result Demonstrates efficacy on datasets with known unfair biases.
The paper addresses fairness issues in screening classifiers, proposing within-group monotonicity to avoid unfair treatment of qualified candidates.
problem Within-group unfairness in screening classifiers using calibrated models.
method Introducing within-group monotonicity as a property to avoid unfair treatment and developing an efficient post-processing algorithm based on dynamic programming.
result Within-group monotonicity can be achieved efficiently and often at a small cost, improving fairness without significantly compromising prediction accuracy.
Investigates fairness in pipeline models where individuals may drop out.
problem Fairness in pipeline models where individuals may drop out and subsequent stages depend on remaining individuals.
method Rigorous framework for evaluating fairness guarantees, showing that naïve auditing is insufficient and dependence must exist between stages.
result Fairness in pipelines can be arbitrary, even with just two stages, and requires dependence between stages.
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.
This research compares two encoding methods for categorical attributes in machine learning, affecting model fairness.
problem The impact of encoding protected categorical attributes on fairness in machine learning models.
method Comparison of one-hot encoding and target encoding methods.
result Target encoding can lead to more unfair models compared to one-hot encoding due to induced bias.
New classifier avoids unfair treatment using robust log loss.
problem Ensuring fairness in classification models for social applications.
method Derives a new classifier from distributional robustness, incorporating fairness criteria into worst-case logarithmic loss minimization.
result Shows practical advantages in three fairness datasets.
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.
Proposes a method to learn fair and transferable representations.
problem Learning fair and transferable data representations.
method Information-theoretic objective with expressiveness-fairness trade-off control.
result Demonstrates higher expressiveness at lower computational cost compared to existing methods.
Generative models can be unfair and unstable; new methods improve fairness and stability.
problem Generative models unfairly penalize minority data and suffer from MADness.
method Intentionally designed hypernetworks and regularization terms.
result Generative models are more fair, stable, and unbiased with new methods.
Study examines how people perceive fairness in criminal risk prediction algorithms.
problem Concerns about fairness in algorithmic decision making, especially in criminal risk prediction.
method Survey of 576 people to understand perceptions of fairness in algorithmic decision making.
result People's fairness judgments are influenced by eight latent properties of features in algorithms.
Paper proposes a federated learning framework for relative fairness.
problem Traditional fairness in federated learning overlooks performance disparities between client subgroups.
method Uses a minimax problem approach to minimize relative unfairness, introducing a fairness index based on loss ratios.
result Empirical evaluations confirm the framework's effectiveness in maintaining model performance while reducing disparity.
Link quandles are shown to be residually finite.
problem Residual finiteness of link quandles.
method Proving residual finiteness of free products of residually finite quandles with residually finite associated groups.
result Link quandles are residually finite.
Free and knot quandles are residually finite.
problem Residual finiteness of quandles.
method Definition and investigation of residual finiteness; proof for free and knot quandles; discussion on automorphism groups.
result Free and knot quandles are residually finite and Hopfian.