Sample-Specific Root Causal Inference with Latent Variables
This work addresses root cause analysis for disease diagnosis, but it is incremental as it relaxes the no-latent-confounding assumption from prior research.
The paper tackles the problem of sample-specific root causal inference in the presence of latent confounding among predictors, introducing the EEL algorithm to recover error terms and compute Shapley values efficiently. Experiments show that EEL achieves superior accuracy and robustness compared to previous methods.
Root causal analysis seeks to identify the set of initial perturbations that induce an unwanted outcome. In prior work, we defined sample-specific root causes of disease using exogenous error terms that predict a diagnosis in a structural equation model. We rigorously quantified predictivity using Shapley values. However, the associated algorithms for inferring root causes assume no latent confounding. We relax this assumption by permitting confounding among the predictors. We then introduce a corresponding procedure called Extract Errors with Latents (EEL) for recovering the error terms up to contamination by vertices on certain paths under the linear non-Gaussian acyclic model. EEL also identifies the smallest sets of dependent errors for fast computation of the Shapley values. The algorithm bypasses the hard problem of estimating the underlying causal graph in both cases. Experiments highlight the superior accuracy and robustness of EEL relative to its predecessors.