On conditional parity as a notion of non-discrimination in machine learning

Abstract

We identify conditional parity as a general notion of non-discrimination in machine learning. In fact, several recently proposed notions of non-discrimination, including a few counterfactual notions, are instances of conditional parity. We show that conditional parity is amenable to statistical analysis by studying randomization as a general mechanism for achieving conditional parity and a kernel-based test of conditional parity.

References in corpus (5)

• Equality of Opportunity in Supervised Learning
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Counterfactual Fairness
• Kernel-based Conditional Independence Test and Application in Causal Discovery
• On the (im)possibility of fairness

Cited by in corpus (8)

• Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements
• Fairness risk measures
• Bias, Fairness, and Accountability with AI and ML Algorithms
• Debiasing representations by removing unwanted variation due to protected attributes
• Individually Fair Ranking
• Statistical inference for individual fairness
• Non-Comparative Fairness for Human-Auditing and Its Relation to Traditional Fairness Notions
• On the Identification of Fair Auditors to Evaluate Recommender Systems based on a Novel Non-Comparative Fairness Notion