Equalized odds postprocessing under imperfect group information

Abstract

Most approaches aiming to ensure a model's fairness with respect to a protected attribute (such as gender or race) assume to know the true value of the attribute for every data point. In this paper, we ask to what extent fairness interventions can be effective even when only imperfect information about the protected attribute is available. In particular, we study the prominent equalized odds postprocessing method of Hardt et al. (2016) under a perturbation of the attribute. We identify conditions on the perturbation that guarantee that the bias of a classifier is reduced even by running equalized odds with the perturbed attribute. We also study the error of the resulting classifier. We empirically observe that under our identified conditions most often the error does not suffer from a perturbation of the protected attribute. For a special case, we formally prove this observation to be true.

References in corpus (15)

• Equality of Opportunity in Supervised Learning
• The Measure and Mismeasure of Fairness
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• On Fairness and Calibration
• Fairness Without Demographics in Repeated Loss Minimization
• Learning Non-Discriminatory Predictors
• The Price of Fair PCA: One Extra Dimension
• Fair and Diverse DPP-based Data Summarization
• Guarantees for Spectral Clustering with Fairness Constraints
• Fair Coresets and Streaming Algorithms for Fair k-Means Clustering
• The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric
• Noise-tolerant fair classification
• Proxy Fairness
• Multi-Criteria Dimensionality Reduction with Applications to Fairness
• Hierarchical VampPrior Variational Fair Auto-Encoder

Cited by in corpus (6)

• Fairness without Demographics through Adversarially Reweighted Learning
• Fair Learning with Private Demographic Data
• Group fairness without demographics using social networks
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach
• Probabilistic Fair Clustering
• Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss