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 (15)

• Equality of Opportunity in Supervised Learning
• 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 Convex Framework for Fair Regression
• From Parity to Preference-based Notions of Fairness in Classification
• A Note on the PAC Bayesian Theorem
• A statistical framework for fair predictive algorithms
• Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models
• Provably Fair Representations
• Two-stage Algorithm for Fairness-aware Machine Learning
• Spectral Algorithms for Computing Fair Support Vector Machines
• Discriminatory Transfer
• Fair Classification and Social Welfare

Cited by in corpus (17)

• LiFT: A Scalable Framework for Measuring Fairness in ML Applications
• Improving the Fairness of Deep Generative Models without Retraining
• Achieving Equalized Odds by Resampling Sensitive Attributes
• Conditional Learning of Fair Representations
• Motif-driven Dense Subgraph Discovery in Directed and Labeled Networks
• Predicting Early Dropout: Calibration and Algorithmic Fairness Considerations
• 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
• Fairness with Continuous Optimal Transport
• Whither Fair Clustering?
• Leveraging Administrative Data for Bias Audits: Assessing Disparate Coverage with Mobility Data for COVID-19 Policy
• Fairness-Aware Online Personalization
• Fair for All: Best-effort Fairness Guarantees for Classification
• Sifter: A Hybrid Workflow for Theme-based Video Curation at Scale
• Methodological Blind Spots in Machine Learning Fairness: Lessons from the Philosophy of Science and Computer Science
• How Personal is Machine Learning Personalization?