Equality of Opportunity in Supervised Learning

Abstract

We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy. In line with other studies, our notion is oblivious: it depends only on the joint statistics of the predictor, the target and the protected attribute, but not on interpretation of individualfeatures. We study the inherent limits of defining and identifying biases based on such oblivious measures, outlining what can and cannot be inferred from different oblivious tests. We illustrate our notion using a case study of FICO credit scores.

References in corpus (1)

• On the relation between accuracy and fairness in binary classification

Cited by in corpus (605)

• Interpretable machine learning: definitions, methods, and applications
• Shortcut Learning in Deep Neural Networks
• Counterfactual Fairness
• The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies
• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
• A review of domain adaptation without target labels
• Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions
• Fairness of Exposure in Rankings
• The What-If Tool: Interactive Probing of Machine Learning Models
• Fairness in Machine Learning: A Survey
• FA*IR: A Fair Top-k Ranking Algorithm
• The Measure and Mismeasure of Fairness
• Machine Learning and Deep Learning -- A review for Ecologists
• Fairness in Machine Learning: Lessons from Political Philosophy
• Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
• Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search
• Fair Resource Allocation in Federated Learning
• On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
• Fairness in Machine Learning
• 50 Years of Test (Un)fairness: Lessons for Machine Learning
• Towards a Critical Race Methodology in Algorithmic Fairness
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• Out-of-Distribution Generalization via Risk Extrapolation (REx)
• Towards Out-Of-Distribution Generalization: A Survey
• A Clarification of the Nuances in the Fairness Metrics Landscape
• User-oriented Fairness in Recommendation
• A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
• A Convex Framework for Fair Regression
• Fairness in Credit Scoring: Assessment, Implementation and Profit Implications
• Learning Adversarially Fair and Transferable Representations
• An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction
• A Field Guide to Federated Optimization
• On Formalizing Fairness in Prediction with Machine Learning
• Predictive Inequity in Object Detection
• FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age
• Personalized Counterfactual Fairness in Recommendation
• Connecting User and Item Perspectives in Popularity Debiasing for Collaborative Recommendation
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• Interpreting Blackbox Models via Model Extraction
• Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning
• Satisfying Real-world Goals with Dataset Constraints
• Operational Research: Methods and Applications
• Identifying and Correcting Label Bias in Machine Learning
• Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction
• Women also Snowboard: Overcoming Bias in Captioning Models
• Racial categories in machine learning
• Machine Learning Testing: Survey, Landscapes and Horizons
• A Reductions Approach to Fair Classification
• Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems
• Does Object Recognition Work for Everyone?
• Auditing for Discrimination in Algorithms Delivering Job Ads
• Aligning AI With Shared Human Values
• Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
• Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations
• Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
• Conservative AI and social inequality: Conceptualizing alternatives to bias through social theory
• Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation
• Unsolved Problems in ML Safety
• Operationalizing Individual Fairness with Pairwise Fair Representations
• Empirical Risk Minimization under Fairness Constraints
• A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
• Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
• An Investigation of Why Overparameterization Exacerbates Spurious Correlations
• Residual Unfairness in Fair Machine Learning from Prejudiced Data
• Bias in Machine Learning Models Can Be Significantly Mitigated by Careful Training: Evidence from Neuroimaging Studies
• InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity
• Causal Reasoning for Algorithmic Fairness
• Differential Privacy Has Disparate Impact on Model Accuracy
• Rule Extraction in Unsupervised Anomaly Detection for Model Explainability: Application to OneClass SVM
• Keeping Community in the Loop: Understanding Wikipedia Stakeholder Values for Machine Learning-Based Systems
• What's Sex Got To Do With Fair Machine Learning?
• Fair Regression: Quantitative Definitions and Reduction-based Algorithms
• Aequitas: A Bias and Fairness Audit Toolkit
• Fair Regression for Health Care Spending
• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
• Implicit Graph Neural Networks
• Machine learning fairness notions: Bridging the gap with real-world applications
• Visual Analysis of Discrimination in Machine Learning
• Towards Equity and Algorithmic Fairness in Student Grade Prediction
• Bringing the People Back In: Contesting Benchmark Machine Learning Datasets
• Fairness in Risk Assessment Instruments: Post-Processing to Achieve Counterfactual Equalized Odds
• Bias in Machine Learning -- What is it Good for?
• Out of Distribution Generalization in Machine Learning
• LiFT: A Scalable Framework for Measuring Fairness in ML Applications
• Four Years of FAccT: A Reflexive, Mixed-Methods Analysis of Research Contributions, Shortcomings, and Future Prospects
• Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems
• Fairness without Demographics through Adversarially Reweighted Learning
• Characterising Bias in Compressed Models
• Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making
• How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness
• Fairness in machine learning: against false positive rate equality as a measure of fairness
• Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey
• Awareness in Practice: Tensions in Access to Sensitive Attribute Data for Antidiscrimination
• Fair k-Center Clustering for Data Summarization
• Robust Optimization for Fairness with Noisy Protected Groups
• Mitigating Gender Bias in Natural Language Processing: Literature Review
• FairGAN: Fairness-aware Generative Adversarial Networks
• Mitigating Bias in Federated Learning
• Fairness for Robust Log Loss Classification
• Policy Learning for Fairness in Ranking
• Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
• A survey on datasets for fairness-aware machine learning
• Survey on Causal-based Machine Learning Fairness Notions
• Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features
• Finite Versus Infinite Neural Networks: an Empirical Study
• Optimized Data Pre-Processing for Discrimination Prevention
• Data Privacy and Trustworthy Machine Learning
• Inherent Limitations of AI Fairness
• On Adversarial Bias and the Robustness of Fair Machine Learning
• Unbiased Graph Embedding with Biased Graph Observations
• FairBatch: Batch Selection for Model Fairness
• Responsible AI by Design in Practice
• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
• What's in a Name? Reducing Bias in Bios without Access to Protected Attributes
• Fair Coresets and Streaming Algorithms for Fair k-Means Clustering
• Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
• A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges
• Improving Fairness via Federated Learning
• Towards Understanding Fairness and its Composition in Ensemble Machine Learning
• Towards Individual and Multistakeholder Fairness in Tourism Recommender Systems
• The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric
• Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination
• Visus: An Interactive System for Automatic Machine Learning Model Building and Curation
• The Sensitivity of Counterfactual Fairness to Unmeasured Confounding
• Blind Justice: Fairness with Encrypted Sensitive Attributes
• Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
• A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoption
• Individual Fairness for $k$-Clustering
• Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees
• Noise-tolerant fair classification
• Out of Context: Investigating the Bias and Fairness Concerns of "Artificial Intelligence as a Service"
• On the Legal Compatibility of Fairness Definitions
• Algorithmic Unfairness through the Lens of EU Non-Discrimination Law: Or Why the Law is not a Decision Tree
• Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings
• Learning Certified Individually Fair Representations
• Inherent Tradeoffs in Learning Fair Representations
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
• Improved Adversarial Learning for Fair Classification
• Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements
• Algorithmic Decision Making with Conditional Fairness
• Average Individual Fairness: Algorithms, Generalization and Experiments
• Transfer of Machine Learning Fairness across Domains
• Robustness Disparities in Commercial Face Detection
• Optimal Decision Making Under Strategic Behavior
• Fair Learning with Private Demographic Data
• Fairness in Criminal Justice Risk Assessments: The State of the Art
• Appropriate Fairness Perceptions? On the Effectiveness of Explanations in Enabling People to Assess the Fairness of Automated Decision Systems
• Assaying Out-Of-Distribution Generalization in Transfer Learning
• Fair and Diverse Allocation of Scarce Resources
• Fairness risk measures
• Towards Fair Graph Neural Networks via Graph Counterfactual
• RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR
• Whither Bias Goes, I Will Go: An Integrative, Systematic Review of Algorithmic Bias Mitigation
• Algorithmic decision making methods for fair credit scoring
• Fairness without the sensitive attribute via Causal Variational Autoencoder
• Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
• Wasserstein Fair Classification
• Reducing Sentiment Bias in Language Models via Counterfactual Evaluation
• Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference
• Fairness Evaluation in Presence of Biased Noisy Labels
• Recent advances in deep learning theory
• Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation
• Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning
• Improving the Fairness of Deep Generative Models without Retraining
• Directional Bias Amplification
• End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
• Avoiding Disparity Amplification under Different Worldviews
• FACT: A Diagnostic for Group Fairness Trade-offs
• Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
• Towards a Unified Framework for Fair and Stable Graph Representation Learning
• Fairness-Aware Learning with Prejudice Free Representations
• Evaluation of group fairness measures in student performance prediction problems
• Achieving Equalized Odds by Resampling Sensitive Attributes
• Explainability for fair machine learning
• Justice in Misinformation Detection Systems: An Analysis of Algorithms, Stakeholders, and Potential Harms
• Review of Mathematical frameworks for Fairness in Machine Learning
• On conditional parity as a notion of non-discrimination in machine learning
• Fair Oversampling Technique using Heterogeneous Clusters
• Fair Allocation through Selective Information Acquisition
• A Distributionally Robust Approach to Fair Classification
• FairFaceGAN: Fairness-aware Facial Image-to-Image Translation
• Ensuring Fairness Beyond the Training Data
• Fairwashing: the risk of rationalization
• Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks
• Training Fair Models in Federated Learning without Data Privacy Infringement
• Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
• Achieving Fairness in the Stochastic Multi-armed Bandit Problem
• On Fair Selection in the Presence of Implicit and Differential Variance
• Enforcing Group Fairness in Algorithmic Decision Making: Utility Maximization Under Sufficiency
• Popularity Bias in Recommendation: A Multi-stakeholder Perspective
• Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning
• An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision
• Differentially Private Fair Learning
• Knowing what you know: valid and validated confidence sets in multiclass and multilabel prediction
• Fairness-Aware Explainable Recommendation over Knowledge Graphs
• Equalized odds postprocessing under imperfect group information
• Adversarial training approach for local data debiasing
• Open Problems in Cooperative AI
• Auditing and Achieving Intersectional Fairness in Classification Problems
• Conditional Learning of Fair Representations
• xGEMs: Generating Examplars to Explain Black-Box Models
• No computation without representation: Avoiding data and algorithm biases through diversity
• FairCanary: Rapid Continuous Explainable Fairness
• Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks
• Software Engineering for Fairness: A Case Study with Hyperparameter Optimization
• Tuning Fairness by Balancing Target Labels
• FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency
• Fairness-aware Classification: Criterion, Convexity, and Bounds
• Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
• REPAIR: Removing Representation Bias by Dataset Resampling
• BeFair: Addressing Fairness in the Banking Sector
• Multi-Objective Automatic Machine Learning with AutoxgboostMC
• Welfare and Distributional Impacts of Fair Classification
• Proposed Guidelines for the Responsible Use of Explainable Machine Learning
• FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning
• Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
• Axes for Sociotechnical Inquiry in AI Research
• Envy-Free Classification
• Fair Generative Modeling via Weak Supervision
• Decisions, Counterfactual Explanations and Strategic Behavior
• Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints
• Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML
• Measuring justice in machine learning
• Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?
• Extending the Machine Learning Abstraction Boundary: A Complex Systems Approach to Incorporate Societal Context
• FAIR: Fairness-Aware Information Retrieval Evaluation
• Rényi Fair Inference
• Capuchin: Causal Database Repair for Algorithmic Fairness
• Utility is in the Eye of the User: A Critique of NLP Leaderboards
• FNNC: Achieving Fairness through Neural Networks
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
• Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
• Removing the influence of a group variable in high-dimensional predictive modelling
• Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness
• All of the Fairness for Edge Prediction with Optimal Transport
• Characterizing Fairness Over the Set of Good Models Under Selective Labels
• FR-Train: A Mutual Information-Based Approach to Fair and Robust Training
• Wasserstein-based fairness interpretability framework for machine learning models
• Same-Day Delivery with Fairness
• Fairness with Overlapping Groups
• Demographic Bias: A Challenge for Fingervein Recognition Systems?
• Privacy for All: Demystify Vulnerability Disparity of Differential Privacy against Membership Inference Attack
• Online Abuse toward Candidates during the UK General Election 2019: Working Paper
• Loss-Aversively Fair Classification
• Accounting for Model Uncertainty in Algorithmic Discrimination
• Causal Interventions for Fairness
• Learning Interpretable Models with Causal Guarantees
• Achieving Model Fairness in Vertical Federated Learning
• Fair Classification via Domain Adaptation: A Dual Adversarial Learning Approach
• Challenges in Automated Debiasing for Toxic Language Detection
• Societal Biases in Language Generation: Progress and Challenges
• SoK: Machine Learning Governance
• Fair Mixup: Fairness via Interpolation
• Group Fairness in Prediction-Based Decision Making: From Moral Assessment to Implementation
• Fairness guarantee in multi-class classification
• Counterexample-Guided Learning of Monotonic Neural Networks
• Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning
• Fair Machine Guidance to Enhance Fair Decision Making in Biased People
• Fair-Net: A Network Architecture For Reducing Performance Disparity Between Identifiable Sub-Populations
• Achieve Fairness without Demographics for Dermatological Disease Diagnosis
• Is calibration a fairness requirement? An argument from the point of view of moral philosophy and decision theory
• Progressive Disclosure: Designing for Effective Transparency
• Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems
• Removing biased data to improve fairness and accuracy
• Label-Imbalanced and Group-Sensitive Classification under Overparameterization
• Ethical Adversaries: Towards Mitigating Unfairness with Adversarial Machine Learning
• Counterfactual Reasoning for Fair Clinical Risk Prediction
• Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
• Adversarial Removal of Demographic Attributes from Text Data
• Bias, Fairness, and Accountability with AI and ML Algorithms
• Contrastive Examples for Addressing the Tyranny of the Majority
• Joint Fairness Model with Applications to Risk Predictions for Under-represented Populations
• Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy
• On Tilted Losses in Machine Learning: Theory and Applications
• Interpretable and Fair Boolean Rule Sets via Column Generation
• Regulatory Instruments for Fair Personalized Pricing
• Environment Inference for Invariant Learning
• README: REpresentation learning by fairness-Aware Disentangling MEthod
• Discriminatory Transfer
• Evaluation of Fairness Trade-offs in Predicting Student Success
• A survey of bias in Machine Learning through the prism of Statistical Parity for the Adult Data Set
• CaPC Learning: Confidential and Private Collaborative Learning
• Predicting Early Dropout: Calibration and Algorithmic Fairness Considerations
• AI Fairness via Domain Adaptation
• Improving the Generalization of End-to-End Driving through Procedural Generation
• A Human-Centric Perspective on Fairness and Transparency in Algorithmic Decision-Making
• Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features
• An investigation of structures responsible for gender bias in BERT and DistilBERT
• Fair-SSL: Building fair ML Software with less data
• Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data
• Fairness of Exposure in Stochastic Bandits
• Characterizing Intersectional Group Fairness with Worst-Case Comparisons
• Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings
• On Statistical Discrimination as a Failure of Social Learning: A Multi-Armed Bandit Approach
• Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability
• Deontological Ethics By Monotonicity Shape Constraints
• Fair Decisions Despite Imperfect Predictions
• Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy
• The stochastic multi-gradient algorithm for multi-objective optimization and its application to supervised machine learning
• Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees
• Online and Customizable Fairness-aware Learning
• Learning Fair and Transferable Representations
• Online Abuse of UK MPs from 2015 to 2019: Working Paper
• Fairness-aware Model-agnostic Positive and Unlabeled Learning
• Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models
• Incorporating Priors with Feature Attribution on Text Classification
• Unified Group Fairness on Federated Learning
• Towards Logical Specification of Statistical Machine Learning
• Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns
• Approximation Algorithms for Socially Fair Clustering
• FairST: Equitable Spatial and Temporal Demand Prediction for New Mobility Systems
• Multi-objective Asynchronous Successive Halving
• Investigating Bias in Image Classification using Model Explanations
• Disentangled Representations from Non-Disentangled Models
• On the Fairness of Disentangled Representations
• Counterfactual fairness: removing direct effects through regularization
• A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models
• Fairkit, Fairkit, on the Wall, Who's the Fairest of Them All? Supporting Data Scientists in Training Fair Models
• Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation
• Vertical Allocation-based Fair Exposure Amortizing in Ranking
• Statistical Equity: A Fairness Classification Objective
• Analysis of Trade-offs in Fair Principal Component Analysis Based on Multi-objective Optimization
• To Split or Not to Split: The Impact of Disparate Treatment in Classification
• Learning Fair Rule Lists
• Forks Over Knives: Predictive Inconsistency in Criminal Justice Algorithmic Risk Assessment Tools
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision
• Fairness in Forecasting and Learning Linear Dynamical Systems
• Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
• Discovering Fair Representations in the Data Domain
• Addressing multiple metrics of group fairness in data-driven decision making
• FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes
• Does enforcing fairness mitigate biases caused by subpopulation shift?
• Active Sampling for Min-Max Fairness
• Perfectly Parallel Fairness Certification of Neural Networks
• Crank up the volume: preference bias amplification in collaborative recommendation
• Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
• Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
• A toolkit of dilemmas: Beyond debiasing and fairness formulas for responsible AI/ML
• Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
• Ensuring Fairness with Transparent Auditing of Quantitative Bias in AI Systems
• On the Privacy Risks of Algorithmic Fairness
• Fair Clustering with Multiple Colors
• Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithm
• Reinforcement Learning for Fair Dynamic Pricing
• On the Problem of Underranking in Group-Fair Ranking
• Towards Self-Regulating AI: Challenges and Opportunities of AI Model Governance in Financial Services
• RecRec: Algorithmic Recourse for Recommender Systems
• Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders
• Stereotype-Free Classification of Fictitious Faces
• An Examination of Fairness of AI Models for Deepfake Detection
• A Bandit-Based Algorithm for Fairness-Aware Hyperparameter Optimization
• Fair Sequential Selection Using Supervised Learning Models
• What will it take to generate fairness-preserving explanations?
• Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing
• With Malice Towards None: Assessing Uncertainty via Equalized Coverage
• Comparing Human and Machine Bias in Face Recognition
• Improving Fairness in Criminal Justice Algorithmic Risk Assessments Using Conformal Prediction Sets
• Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting
• What About Applied Fairness?
• Dynamic Modeling and Equilibria in Fair Decision Making
• Debiasing representations by removing unwanted variation due to protected attributes
• An Effective, Robust and Fairness-aware Hate Speech Detection Framework
• A Framework for Fairness in Two-Sided Marketplaces
• In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
• Can Active Learning Preemptively Mitigate Fairness Issues?
• Improving Fairness in Adaptive Social Exergames via Shapley Bandits
• Using Positive Matching Contrastive Loss with Facial Action Units to mitigate bias in Facial Expression Recognition
• Group fairness without demographics using social networks
• Fairness in Forecasting of Observations of Linear Dynamical Systems
• Task-Adaptive Neural Network Search with Meta-Contrastive Learning
• Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
• Maximum Weighted Loss Discrepancy
• Adaptive Sampling for Minimax Fair Classification
• Wasserstein Robust Classification with Fairness Constraints
• Principal Fairness: Removing Bias via Projections
• Understanding and Mitigating Accuracy Disparity in Regression
• Classification with abstention but without disparities
• Information Theoretic Measures for Fairness-aware Feature Selection
• Technical Challenges for Training Fair Neural Networks
• Unbiased Subdata Selection for Fair Classification: A Unified Framework and Scalable Algorithms
• FairXGBoost: Fairness-aware Classification in XGBoost
• Avoiding Resentment Via Monotonic Fairness
• A Sequentially Fair Mechanism for Multiple Sensitive Attributes
• Selective Classification Can Magnify Disparities Across Groups
• Impossibility results for fair representations
• Teacher's pet: understanding and mitigating biases in distillation
• Group Fairness in Bandit Arm Selection
• Feature Relevance Determination for Ordinal Regression in the Context of Feature Redundancies and Privileged Information
• Equal Opportunity in Online Classification with Partial Feedback
• Towards Threshold Invariant Fair Classification
• When Fair Classification Meets Noisy Protected Attributes
• Reading Between the Demographic Lines: Resolving Sources of Bias in Toxicity Classifiers
• Distributed generation of privacy preserving data with user customization
• Augmented Fairness: An Interpretable Model Augmenting Decision-Makers' Fairness
• Fairness-Aware Recommendation of Information Curators
• Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation
• Optimal Training of Fair Predictive Models
• Learning Individually Fair Classifier with Path-Specific Causal-Effect Constraint
• Hierarchical Bayesian Models to Mitigate Systematic Disparities in Prediction with Proxy Outcomes
• Tilted Empirical Risk Minimization
• DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
• A Possibility in Algorithmic Fairness: Can Calibration and Equal Error Rates Be Reconciled?
• Fairness as Equality of Opportunity: Normative Guidance from Political Philosophy
• Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity
• Near Neighbor: Who is the Fairest of Them All?
• Fair Classification and Social Welfare
• (Un)fairness in Post-operative Complication Prediction Models
• Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity
• A Stochastic Alternating Balance $k$-Means Algorithm for Fair Clustering
• Fairness and Missing Values
• InfoFair: Information-Theoretic Intersectional Fairness
• Achievement and Fragility of Long-term Equitability
• Towards Return Parity in Markov Decision Processes
• Intersectionality and Testimonial Injustice in Medical Records
• Fairness Through Counterfactual Utilities
• Retiring Adult: New Datasets for Fair Machine Learning
• FairCal: Fairness Calibration for Face Verification
• Stakeholder-in-the-Loop Fair Decisions: A Framework to Design Decision Support Systems in Public and Private Organizations
• Communication-Efficient Agnostic Federated Averaging
• Shedding light on underrepresentation and Sampling Bias in machine learning
• Cohort Shapley value for algorithmic fairness
• Median Optimal Treatment Regimes
• Fairness Through Regularization for Learning to Rank
• An Information-theoretic Approach to Distribution Shifts
• Fair Hate Speech Detection through Evaluation of Social Group Counterfactuals
• Metrics and methods for a systematic comparison of fairness-aware machine learning algorithms
• Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial
• Fairness criteria through the lens of directed acyclic graphical models
• Effects of algorithmic flagging on fairness: quasi-experimental evidence from Wikipedia
• Inclusive GAN: Improving Data and Minority Coverage in Generative Models
• Fairness in Missing Data Imputation
• Solution manifold and Its Statistical Applications
• Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
• Optimizing Generalized Rate Metrics through Game Equilibrium
• Priority-based Post-Processing Bias Mitigation for Individual and Group Fairness
• Pairwise Fairness for Ranking and Regression
• Individually Fair Ranking
• Abstracting Fairness: Oracles, Metrics, and Interpretability
• FairNN- Conjoint Learning of Fair Representations for Fair Decisions
• Beyond Individual and Group Fairness
• Random walks with local memory
• Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
• Correspondences between Privacy and Nondiscrimination: Why They Should Be Studied Together
• The Random Conditional Distribution for Higher-Order Probabilistic Inference
• Fair Data Representation for Machine Learning at the Pareto Frontier
• Metadata Normalization
• The Social Cost of Strategic Classification
• Fair Decision Rules for Binary Classification
• Identifying biases in legal data: An algorithmic fairness perspective
• Learning Fairness-aware Relational Structures
• Quantifying Infra-Marginality and Its Trade-off with Group Fairness
• On the Impact of Data Quality on Image Classification Fairness
• Statistical inference for individual fairness
• Multi-group Agnostic PAC Learnability
• Biased Models Have Biased Explanations
• Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP
• Linear Classifiers that Encourage Constructive Adaptation
• Responsible AI Challenges in End-to-end Machine Learning
• Fairness in Deep Learning: A Computational Perspective
• Uncovering the Bias in Facial Expressions
• Fairness on Synthetic Visual and Thermal Mask Images
• RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity
• Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification
• Probabilistic Fair Clustering
• Additive Adversarial Learning for Unbiased Authentication
• Fairness in Ranking under Uncertainty
• Towards a Measure of Individual Fairness for Deep Learning
• Assessing Disparate Impacts of Personalized Interventions: Identifiability and Bounds
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach
• Algorithmic Bias in Recidivism Prediction: A Causal Perspective
• A Primal-Dual Subgradient Approachfor Fair Meta Learning
• Fairness Constraints in Semi-supervised Learning
• Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
• Fair Normalizing Flows
• Transitioning from Real to Synthetic data: Quantifying the bias in model
• Mitigating Gender Bias in Captioning Systems
• Oblivious Data for Fairness with Kernels
• Generating private data with user customization
• Locating disparities in machine learning
• A Pre-processing Method for Fairness in Ranking
• Randomized Classifiers vs Human Decision-Makers: Trustworthy AI May Have to Act Randomly and Society Seems to Accept This
• Achieving non-discrimination in prediction
• Online Fairness-Aware Learning with Imbalanced Data Streams
• The Sharpe predictor for fairness in machine learning
• Inherent Trade-offs in the Fair Allocation of Treatments
• Making ML models fairer through explanations: the case of LimeOut
• An example of prediction which complies with Demographic Parity and equalizes group-wise risks in the context of regression
• Metric-Free Individual Fairness with Cooperative Contextual Bandits
• Debiasing Convolutional Neural Networks via Meta Orthogonalization
• Fair quantile regression
• Improving Counterfactual Generation for Fair Hate Speech Detection
• Generative Models for Security: Attacks, Defenses, and Opportunities
• Fairness-guided SMT-based Rectification of Decision Trees and Random Forests
• A Fully Bayesian, Logistic Regression Tracking Algorithm for Mitigating Disparate Misclassification
• Fair for All: Best-effort Fairness Guarantees for Classification
• A Distributed Fair Machine Learning Framework with Private Demographic Data Protection
• Recommending Dream Jobs in a Biased Real World
• One-vs.-One Mitigation of Intersectional Bias: A General Method to Extend Fairness-Aware Binary Classification
• Detecting discriminatory risk through data annotation based on Bayesian inferences
• Beyond traditional assumptions in fair machine learning
• Learning Fair Representations for Recommendation: A Graph-based Perspective
• Maxmin-Fair Ranking: Individual Fairness under Group-Fairness Constraints
• Provably Training Overparameterized Neural Network Classifiers with Non-convex Constraints
• Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
• The Cost of a Reductions Approach to Private Fair Optimization
• Fair Resource Allocation for Demands with Sharp Lower Tail Inequalities
• OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learning
• Towards the Right Kind of Fairness in AI
• Model Mis-specification and Algorithmic Bias
• Fairness-aware Outlier Ensemble
• Fair Sparse Regression with Clustering: An Invex Relaxation for a Combinatorial Problem
• Hidden Technical Debts for Fair Machine Learning in Financial Services
• Affirmative Action Policies for Top-k Candidates Selection, With an Application to the Design of Policies for University Admissions
• Obstructing Classification via Projection
• Enumerating Fair Packages for Group Recommendations
• Explainability-aided Domain Generalization for Image Classification
• Positivity-free Policy Learning with Observational Data
• Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss
• Towards classification parity across cohorts
• Fair Classification with Adversarial Perturbations
• Faking Fairness via Stealthily Biased Sampling
• Mitigating Voter Attribute Bias for Fair Opinion Aggregation
• From Fair Decision Making to Social Equality
• Probabilistic Verification of Fairness Properties via Concentration
• Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
• Fairness-Aware Online Personalization
• "I had a solid theory before but it's falling apart": Polarizing Effects of Algorithmic Transparency
• Grading video interviews with fairness considerations
• "And the Winner Is...": Dynamic Lotteries for Multi-group Fairness-Aware Recommendation
• Adaptation and Generalization for Unknown Sensitive Factors of Variations
• Fairness-aware Summarization for Justified Decision-Making
• DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
• Fair treatment allocations in social networks
• Equalizing Financial Impact in Supervised Learning
• Fair Meta-Learning: Learning How to Learn Fairly
• The Fair Game: Auditing & Debiasing AI Algorithms Over Time
• Women also Snowboard: Overcoming Bias in Captioning Models (Extended Abstract)
• (Un)certainty of (Un)fairness: Preference-Based Selection of Certainly Fair Decision-Makers
• On Constraint Definability in Tractable Probabilistic Models
• Fair Adversarial Networks
• GroupMixNorm Layer for Learning Fair Models
• The invisible power of fairness. How machine learning shapes democracy
• Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility
• Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice models
• Adversarial Regression with Doubly Non-negative Weighting Matrices
• Enhancing Model Robustness and Fairness with Causality: A Regularization Approach
• Federating for Learning Group Fair Models
• Towards More Accountable Search Engines: Online Evaluation of Representation Bias
• Getting Fairness Right: Towards a Toolbox for Practitioners
• Fair Clustering Through Fairlets
• Machine Learning for Temporal Data in Finance: Challenges and Opportunities
• Leave-one-out Unfairness
• Fairness for Whom? Critically reframing fairness with Nash Welfare Product
• On the impossibility of non-trivial accuracy under fairness constraints
• Slice Tuner: A Selective Data Acquisition Framework for Accurate and Fair Machine Learning Models
• Unfairness Discovery and Prevention For Few-Shot Regression
• Legally grounded fairness objectives
• Differentially Private and Fair Classification via Calibrated Functional Mechanism
• Stateful Strategic Regression
• On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond
• Learning to Collaborate for User-Controlled Privacy
• Access to Population-Level Signaling as a Source of Inequality
• Data Management for Causal Algorithmic Fairness
• Digital Normativity: A challenge for human subjectivization and free will
• Invariant Representations with Stochastically Quantized Neural Networks
• Learning Models for Actionable Recourse
• Group-based Fair Learning Leads to Counter-intuitive Predictions
• Selective Regression Under Fairness Criteria
• Model-agnostic bias mitigation methods with regressor distribution control for Wasserstein-based fairness metrics
• Reducing Unintended Bias of ML Models on Tabular and Textual Data
• Doing good by fighting fraud: Ethical anti-fraud systems for mobile payments
• Consider the Alternatives: Navigating Fairness-Accuracy Tradeoffs via Disqualification
• Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience
• Topics to Avoid: Demoting Latent Confounds in Text Classification
• Non-Comparative Fairness for Human-Auditing and Its Relation to Traditional Fairness Notions
• Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition
• Local Justice and the Algorithmic Allocation of Societal Resources
• Pairwise Fairness for Ordinal Regression
• Achieving Transparency Report Privacy in Linear Time
• Stacking interventions for equitable outcomes
• The Crossover Process: Learnability and Data Protection from Inference Attacks
• Visions in Theoretical Computer Science: A Report on the TCS Visioning Workshop 2020
• Training Over-parameterized Models with Non-decomposable Objectives
• Games for Fairness and Interpretability
• A Cautionary Tail: A Framework and Case Study for Testing Predictive Model Validity
• One Size Fits All: Can We Train One Denoiser for All Noise Levels?
• Towards Auditability for Fairness in Deep Learning
• Fairness-Aware Online Meta-learning
• Towards Integrating Fairness Transparently in Industrial Applications
• Fairness through Equality of Effort
• On the Fairness of Swarm Learning in Skin Lesion Classification
• Outcome Indistinguishability
• Individual Fairness in Hindsight
• Deconfounding age effects with fair representation learning when assessing dementia
• Fairness Properties of Face Recognition and Obfuscation Systems
• Estimation of Fair Ranking Metrics with Incomplete Judgments
• Logic Constraints to Feature Importances
• Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition
• A Sociotechnical View of Algorithmic Fairness
• Equity-Directed Bootstrapping: Examples and Analysis
• Adaptive Data Debiasing through Bounded Exploration
• HyperFair: A Soft Approach to Integrating Fairness Criteria
• Learning the Truth From Only One Side of the Story
• On the Identification of Fair Auditors to Evaluate Recommender Systems based on a Novel Non-Comparative Fairness Notion