Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models

arXiv:2306.11281v3 Announce Type: replace
Abstract: Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when the causal variables are unobserved and the observations are non-linear mixtures of these latent variables, such as pixels in images. One approach is to recover the latent Structural Causal Model (SCM), which may be infeasible in practice due to requiring strong assumptions, e.g., linearity of the causal mechanisms or perfect atomic interventions. Meanwhile, more practical ML-based approaches using naive …

abstract applications arxiv causal counterfactual cs.lg domain explainability fairness images linear non-linear pixels queries robustness stat.me type variables