Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation

arXiv:2404.13798v1 Announce Type: new
Abstract: Conditional independence (CI) constraints are critical for defining and evaluating fairness in machine learning, as well as for learning unconfounded or causal representations. Traditional methods for ensuring fairness either blindly learn invariant features with respect to a protected variable (e.g., race when classifying sex from face images) or enforce CI relative to the protected attribute only on the model output (e.g., the sex label). Neither of these methods are effective in enforcing CI in high-dimensional …

abstract arxiv causal constraints cs.cv fair fairness features image image generation learn machine machine learning race representation representation learning sex type