Develops a method to quantify racial bias in law enforcement systems.
problem Quantify racial bias in law enforcement systems considering criminality and multi-stage interactions.
method Multi-stage causal framework incorporating criminality.
result Identifies three canonical scenarios of racial bias in law enforcement.
Reduces gender classification bias by learning race-invariant face representations.
problem Societal bias in gender recognition systems.
method Adversarially trained autoencoder model to learn race-invariant face representations.
result Achieved a significant drop of over 40% in racial bias surrogate metric with race invariant representations.
Assessing the fairness of a decision making system with respect to a protected class, such as gender or race, is challenging when class membership labels are unavailable. Probabilistic models for predicting the protected class based on observable proxies, such as surname and geolocation for race, are sometimes used to …
Paper debiases multiple word embedding biases simultaneously.
problem Reduction of multiple biases in word embeddings.
method Joint multiclass debiasing approach using Word Embeddings Association Test (WEAT).
result Demonstrates reduction or complete elimination of bias in word embeddings.
Study removes bias from chest X-ray embeddings using orthogonalization.
problem Reduces bias in chest X-ray embeddings due to protected features.
method Orthogonalization technique to remove protected feature effects.
result Orthogonalization removes bias and makes predictions of protected attributes infeasible.
This paper assesses biases in contextualized word representations.
problem Analyzing biases in contextualized word representations.
method Proposes assessing bias at the contextual word level, capturing contextual effects of bias.
result Demonstrates evidence of bias in contextual word models, including racial bias and exacerbated effects for intersectional minorities.
fairadapt uses causal inference to mitigate algorithmic bias in data pre-processing.
problem Mitigating algorithmic bias in machine learning predictions.
method Causal graphical model and observed data to address counterfactual questions.
result The method can help eliminate discrimination and justify fair decisions.
Overlearning exposes hidden, sensitive attributes in models, threatening privacy and bias.
problem Models learn unintended, sensitive attributes beyond their training objectives.
method Demonstrated and analyzed overlearning in vision and NLP models.
result Overlearning reveals sensitive attributes that break privacy protections and can be re-purposed for harmful tasks.
Predictive modeling is increasingly being employed to assist human decision-makers. One purported advantage of replacing human judgment with computer models in high stakes settings-- such as sentencing, hiring, policing, college admissions, and parole decisions-- is the perceived "neutrality" of computers. It is argued…
The paper introduces a new bias measure, infra-marginality, to quantify unfairness in group fairness.
problem The trade-off between group fairness and individual-level bias in decision-making.
method Proposes a new notion of η-infra-marginality, proves its independence from accuracy, and provides practical methods to measure and avoid it. result High accuracy does not lead to high infra-marginality, but maximizing group fairness often increases infra-marginality.
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.
There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, or age. However, this raises two significant challenges: (1) protected attributes may not be available or it may not be legal to use…
Machine learning outperforms crowd investors in predicting loan defaults and investment returns.
problem Determining if machine learning can outperform human decision-making in crowd lending.
method Using data from Prosper.com, a sophisticated ML algorithm was trained to predict loan defaults and investment returns.
result The ML algorithm outperforms crowd investors in predicting loan defaults and investment returns, especially for risky loans.
Federated learning can propagate bias from a few parties to all participants.
problem Bias from a few parties in federated learning can spread to all participants.
method Analysis of naturally partitioned real-world datasets.
result Bias in federated learning is higher than in centralized training.
New method detects bias in AI models that generate data.
problem Detecting bias in AI models that generate data.
method Formalized causal fairness in generative AI, derived new decomposition results, established identification conditions, and introduced efficient estimators.
result Demonstrated the value of new methodology in analyzing bias in large language models.
Algorithm reduces bias in generative models using unlabeled reference data.
problem Detect and mitigate bias in generative models trained on biased datasets.
method Weakly supervised algorithm using density ratio technique and data from both biased and reference datasets.
result Generative models achieve up to 34.6% reduction in bias over baselines.
Develops fair machine learning models resistant to sensitive perturbations.
problem Ensuring model performance is invariant to sensitive attributes like gender and ethnicity.
method Distributionally robust optimization to enforce individual fairness.
result Demonstrates effectiveness on tasks prone to bias.
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.
Securely trains fair models using homomorphic encryption.
problem Protecting sensitive features while testing model fairness.
method Fully homomorphic encryption for training and testing.
result Practical application to adult income data set.
New fair regression method improves fairness in chronic kidney disease classification.
problem Mitigating societal bias in health care for multiple groups.
method Penalized fair regression framework for multiple groups, with penalties for true positive rate disparity.
result Achieves fairness-accuracy frontier beyond existing methods in simulations and real-world data.
Intersectional constraints improve selection outcomes by reducing inequality.
problem Persistent inequality and reduced utility in selection processes due to implicit bias.
method Introducing intersectional constraints to mitigate the adverse effects of implicit bias in selection processes.
result Intersectional constraints can recover almost all the utility achievable in the absence of implicit bias, offering a significant advantage over non-intersectional constraints.
Machine learning algorithms can unintentionally discriminate; tools detect and fix this.
problem Unintentional discrimination in machine learning algorithms.
method Statistical tools to detect and eliminate biases.
result Tools can identify and mitigate algorithmic discrimination.
Paper presents a bias mitigation method using maximum entropy.
problem Bias in datasets due to over/under-representation of groups.
method Maximum entropy principle applied to data preprocessing.
result Achieves target fairness metrics and maintains classifier accuracy.
PEF identifies the best subgroup performance balance for fairness.
problem Fairness constraints can degrade performance in skewed datasets.
method PEF identifies the closest operating point on the Pareto curve of subgroup performances.
result PEF achieves Pareto levels in accuracy for all subgroups.
Proposes a method to increase diversity without sacrificing meritocracy.
problem Systemic bias in datasets affecting diversity and meritocracy.
method Optimally flipping outcome labels and training classification models simultaneously.
result The price of diversity is low and sometimes negative, enhancing diversity without significantly affecting meritocracy.
Develops a learning model predictive controller for competitive racing.
problem Lack of exploration in state space and complexity in obstacle avoidance.
method Explores state space through multiple initializations and develops a new method for convex terminal set selection.
result Yields a richer terminal safe set and maintains convexity.
Modeling horse race betting odds with Ornstein-Uhlenbeck process.
problem Analyzing how herding and informed bettors affect odds movements.
method Deriving an Ornstein-Uhlenbeck process from vote shares and odds movements data.
result Identified microscopic and macroscopic patterns in odds convergence.
Deep RL drone trained to compete against classical path planning in drone racing.
problem Optimizing long-term drone racing strategies using reinforcement learning.
method Used PPO algorithm on a simulated quadrotor in a racing environment created with AirSim.
result Deep RL agent outperformed classical path planning in drone racing competitions.
A new algorithm for fair decision-making in bandit problems with biased feedback.
problem Fair allocation of resources across sensitive groups in bandit problems with biased feedback.
method Proposes a novel algorithm that learns a societal bias term to mitigate unfairness in multi-armed bandit problems.
result The proposed algorithm achieves a theoretical bound on regret and demonstrates fairness in synthetic and real-world data.
New methods ensure fair rankings in web-scale recommender systems.
problem Ensuring fairness in recommender systems, especially in web-scale applications.
method Scalable methods for achieving fairness in rankings, addressing position bias.
result Our methods effectively achieve fairness in various recommender systems.
Paper studies fairness postprocessing with imperfect attribute information.
problem Ensuring fairness with imperfect protected attribute information.
method Equalized odds postprocessing method with imperfect attribute information.
result Conditions on perturbation ensure reduced bias in classifier.
DeepRacing uses neural networks to predict trajectories for autonomous racing in video games.
problem Training algorithms for high-speed autonomous racing in realistic environments.
method Developed a virtual testbed using F1 video games, trained neural networks to predict trajectories and control commands.
result Trajectory prediction outperforms end-to-end control methods in autonomous racing simulations.
Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, w…
Test for fairness in IR systems based on protected variables.
problem Unfairness in IR systems due to correlation with protected variables.
method Statistical test for 'distribution parity' in top-K IR results.
result Ensures fairness in IR systems for all users.
To answer questions about racial inequality and fairness, we often need a way to infer race and ethnicity from names. One way to infer race and ethnicity from names is by relying on the Census Bureau's list of popular last names. The list, however, suffers from at least three limitations: 1. it only contains last names…
Black women and white men have the highest income disparity in the U.S.
problem Income inequality between black women and white men in the USA
method Dynamic microeconomic model, analyzing black and white population income since 1930
result Black females and white males are poles of overall income inequality
Improved race prediction model outperforms existing methods.
problem Improving race prediction using voter registration data.
method Trained BiLSTM model on voter registration data and created an ensemble.
result Achieved up to 36.8% higher OOS F1 scores than previous models.
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.
RankNet forecasts car racing positions with improved accuracy and stability.
problem Forecasting rank positions in car racing, especially considering pit stops.
method Cause-effect decomposition in RankNet, incorporating probabilistic forecasting.
result RankNet outperforms baselines significantly, improving MAE by over 10%.
Improved surname geocoding and name supplements enhance race imputation accuracy.
problem Census data problems affecting race imputation accuracy.
method Fully Bayesian Improved Surname Geocoding (fBISG) and name supplements.
result Significant improvement in race imputation accuracy across all racial groups.
Deep chest X-ray classifiers show bias in predicting diagnoses.
problem Bias in deep learning classifiers predicting diagnoses from chest X-rays.
method Trained convolutional neural networks on multiple public datasets to predict 14 diagnostic labels.
result True positive rates vary significantly among different protected attributes, indicating bias.
New social and economic activities massively exploit big data and machine learning algorithms to do inference on people's lives. Applications include automatic curricula evaluation, wage determination, and risk assessment for credits and loans. Recently, many governments and institutions have raised concerns about the …
ProMoD models human race drivers with probabilistic movement primitives and neural networks.
problem Challenging task of modeling human driver behavior due to variability and complexity.
method Modular framework with Probabilistic Movement Primitives, clothoids, and neural networks.
result Significant advantages in imitation accuracy and robustness compared to other algorithms.
Method debiases alternative data for fair credit underwriting.
problem Bias in alternative data affecting credit underwriting fairness.
method Causal inference applied to machine learning models.
result Improves model accuracy across racial groups without discrimination.
BBE simulates sports betting exchanges for data generation.
problem Creating synthetic data for betting strategy testing.
method Agent-based model (ABM) for sports betting exchange simulation.
result Simulation runs up to 1000 times faster with GPU.
Automated decision making systems are increasingly being used in real-world applications. In these systems for the most part, the decision rules are derived by minimizing the training error on the available historical data. Therefore, if there is a bias related to a sensitive attribute such as gender, race, religion, e…
Fairness in LLMs is impossible due to inherent technical challenges.
problem Ensuring fairness in large language models (LLMs) with rigorous definitions.
method Analysis of various technical fairness frameworks.
result No feasible technical fairness frameworks for LLMs due to large amounts of unstructured data and many potential combinations.
Research aims to ensure fair classification across explicit and implicit sensitive features.
problem Ensuring fairness in machine learning models when sensitive features are not explicitly provided.
method Defined explicit and implicit cohorts, used clustering of embeddings, modified loss function.
result Improved classification parity across explicit and implicit sensitive features.