Exogenous Isomorphism for Counterfactual Identifiability

Code

• github.com/cyisk/tmscm
  OfficialIn paperpytorch★ 0

Abstract

This paper investigates _L_3-identifiability, a form of complete counterfactual identifiability within the Pearl Causal Hierarchy (PCH) framework, ensuring that all Structural Causal Models (SCMs) satisfying the given assumptions provide consistent answers to all causal questions. To simplify this problem, we introduce exogenous isomorphism and propose _EI-identifiability, reflecting the strength of model identifiability required for _L_3-identifiability. We explore sufficient assumptions for achieving _EI-identifiability in two special classes of SCMs: Bijective SCMs (BSCMs), based on counterfactual transport, and Triangular Monotonic SCMs (TM-SCMs), which extend _L_2-identifiability. Our results unify and generalize existing theories, providing theoretical guarantees for practical applications. Finally, we leverage neural TM-SCMs to address the consistency problem in counterfactual reasoning, with experiments validating both the effectiveness of our method and the correctness of the theory.

Tasks

Reproductions