Causal Reasoning for Algorithmic Fairness

Abstract

In this work, we argue for the importance of causal reasoning in creating fair algorithms for decision making. We give a review of existing approaches to fairness, describe work in causality necessary for the understanding of causal approaches, argue why causality is necessary for any approach that wishes to be fair, and give a detailed analysis of the many recent approaches to causality-based fairness.

References in corpus (5)

• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Causal Inference in the Presence of Latent Variables and Selection Bias
• Censoring Representations with an Adversary
• Interventions over Predictions: Reframing the Ethical Debate for Actuarial Risk Assessment

Cited by in corpus (27)

• Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
• Bias in Machine Learning -- What is it Good for?
• Outcome-Explorer: A Causality Guided Interactive Visual Interface for Interpretable Algorithmic Decision Making
• Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
• The Sensitivity of Counterfactual Fairness to Unmeasured Confounding
• What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
• Fairness Evaluation in Presence of Biased Noisy Labels
• Bias in Data-driven AI Systems -- An Introductory Survey
• Causal datasheet: An approximate guide to practically assess Bayesian networks in the real world
• Review of Mathematical frameworks for Fairness in Machine Learning
• Capuchin: Causal Database Repair for Algorithmic Fairness
• Causal Interventions for Fairness
• Subverting Fair Image Search with Generative Adversarial Perturbations
• Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems
• Counterfactual Reasoning for Fair Clinical Risk Prediction
• Counterfactual fairness: removing direct effects through regularization
• The Fairness-Accuracy Pareto Front
• Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
• Combining distributive ethics and causal Inference to make trade-offs between austerity and population health
• Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
• Fairness Through Counterfactual Utilities
• Improving Fair Predictions Using Variational Inference In Causal Models
• Beyond traditional assumptions in fair machine learning
• Investigating Writing Style Development in High School
• Causal Inference in medicine and in health policy, a summary
• Data Management for Causal Algorithmic Fairness
• Shortcomings of Counterfactual Fairness and a Proposed Modification