Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
This addresses fairness issues in classification algorithms for biased data, offering a method to mitigate replication of historical prejudices, though it builds incrementally on prior deep learning and generative modeling work.
The paper tackles the problem of learning from historically biased datasets by proposing a causal modeling approach that accounts for sensitive attributes confounding treatments and outcomes, showing experimentally that it provides better causal effect estimates and helps learn more accurate and fair policies.
How do we learn from biased data? Historical datasets often reflect historical prejudices; sensitive or protected attributes may affect the observed treatments and outcomes. Classification algorithms tasked with predicting outcomes accurately from these datasets tend to replicate these biases. We advocate a causal modeling approach to learning from biased data, exploring the relationship between fair classification and intervention. We propose a causal model in which the sensitive attribute confounds both the treatment and the outcome. Building on prior work in deep learning and generative modeling, we describe how to learn the parameters of this causal model from observational data alone, even in the presence of unobserved confounders. We show experimentally that fairness-aware causal modeling provides better estimates of the causal effects between the sensitive attribute, the treatment, and the outcome. We further present evidence that estimating these causal effects can help learn policies that are both more accurate and fair, when presented with a historically biased dataset.