Fairness in Machine Learning

Abstract

Machine learning based systems are reaching society at large and in many aspects of everyday life. This phenomenon has been accompanied by concerns about the ethical issues that may arise from the adoption of these technologies. ML fairness is a recently established area of machine learning that studies how to ensure that biases in the data and model inaccuracies do not lead to models that treat individuals unfavorably on the basis of characteristics such as e.g. race, gender, disabilities, and sexual or political orientation. In this manuscript, we discuss some of the limitations present in the current reasoning about fairness and in methods that deal with it, and describe some work done by the authors to address them. More specifically, we show how causal Bayesian networks can play an important role to reason about and deal with fairness, especially in complex unfairness scenarios. We describe how optimal transport theory can be used to develop methods that impose constraints on the full shapes of distributions corresponding to different sensitive attributes, overcoming the limitation of most approaches that approximate fairness desiderata by imposing constraints on the lower order moments or other functions of those distributions. We present a unified framework that encompasses methods that can deal with different settings and fairness criteria, and that enjoys strong theoretical guarantees. We introduce an approach to learn fair representations that can generalize to unseen tasks. Finally, we describe a technique that accounts for legal restrictions about the use of sensitive attributes.

References in corpus (33)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
• A Model of Inductive Bias Learning
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• On Fairness and Calibration
• A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
• A Convex Framework for Fair Regression
• Learning Adversarially Fair and Transferable Representations
• On Formalizing Fairness in Prediction with Machine Learning
• Satisfying Real-world Goals with Dataset Constraints
• From Parity to Preference-based Notions of Fairness in Classification
• A Note on the PAC Bayesian Theorem
• Fairness Through Computationally-Bounded Awareness
• Penalizing Unfairness in Binary Classification
• A statistical framework for fair predictive algorithms
• Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer
• Obtaining fairness using optimal transport theory
• Calibration for the (Computationally-Identifiable) Masses
• Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models
• Probably Approximately Metric-Fair Learning
• Provably Fair Representations
• Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification
• Wasserstein Fair Classification
• Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints
• Two-stage Algorithm for Fairness-aware Machine Learning
• Unleashing Linear Optimizers for Group-Fair Learning and Optimization
• Invariant Representations from Adversarially Censored Autoencoders
• Spectral Algorithms for Computing Fair Support Vector Machines
• Discriminatory Transfer
• Learning Fair and Transferable Representations
• Fair Classification and Social Welfare

Cited by in corpus (54)

• Challenges in Deploying Machine Learning: a Survey of Case Studies
• 50 Years of Test (Un)fairness: Lessons for Machine Learning
• A Clarification of the Nuances in the Fairness Metrics Landscape
• A Field Guide to Federated Optimization
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• Fairness in Ranking: A Survey
• Machine learning fairness notions: Bridging the gap with real-world applications
• Equality of Learning Opportunity via Individual Fairness in Personalized Recommendations
• LiFT: A Scalable Framework for Measuring Fairness in ML Applications
• Master your Metrics with Calibration
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• Inherent Tradeoffs in Learning Fair Representations
• The Theory, Practice, and Ethical Challenges of Designing a Diversity-Aware Platform for Social Relations
• Assaying Out-Of-Distribution Generalization in Transfer Learning
• Improving the Fairness of Deep Generative Models without Retraining
• Achieving Equalized Odds by Resampling Sensitive Attributes
• Synthetic Benchmarks for Scientific Research in Explainable Machine Learning
• Conditional Learning of Fair Representations
• BeFair: Addressing Fairness in the Banking Sector
• Utility is in the Eye of the User: A Critique of NLP Leaderboards
• FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imaging
• Improvement-Focused Causal Recourse (ICR)
• Motif-driven Dense Subgraph Discovery in Directed and Labeled Networks
• Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective
• Predicting Early Dropout: Calibration and Algorithmic Fairness Considerations
• Loss Tolerant Federated Learning
• The stochastic multi-gradient algorithm for multi-objective optimization and its application to supervised machine learning
• Analysis of Trade-offs in Fair Principal Component Analysis Based on Multi-objective Optimization
• Representative & Fair Synthetic Data
• Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing
• Fairness through Experimentation: Inequality in A/B testing as an approach to responsible design
• Data and Model Dependencies of Membership Inference Attack
• An Analysis of the Deployment of Models Trained on Private Tabular Synthetic Data: Unexpected Surprises
• Fairness with Continuous Optimal Transport
• Fairness Definitions in Language Models Explained
• Fair Set Cover
• Whither Fair Clustering?
• Managing Bias in Human-Annotated Data: Moving Beyond Bias Removal
• Algorithm Fairness in AI for Medicine and Healthcare
• RAGUEL: Recourse-Aware Group Unfairness Elimination
• Machine Learning Applications for Therapeutic Tasks with Genomics Data
• Machine learning in the social and health sciences
• Some performance considerations when using multi-armed bandit algorithms in the presence of missing data
• Leveraging Administrative Data for Bias Audits: Assessing Disparate Coverage with Mobility Data for COVID-19 Policy
• Fairness-Aware Online Personalization
• Explainability's Gain is Optimality's Loss? -- How Explanations Bias Decision-making
• Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space
• Fair for All: Best-effort Fairness Guarantees for Classification
• The Sharpe predictor for fairness in machine learning
• A Distributed Fair Machine Learning Framework with Private Demographic Data Protection
• Methodological Blind Spots in Machine Learning Fairness: Lessons from the Philosophy of Science and Computer Science
• Sifter: A Hybrid Workflow for Theme-based Video Curation at Scale
• How Personal is Machine Learning Personalization?
• Fairness is in the details: Face Dataset Auditing