Neural Causal Models for Counterfactual Identification and Estimation
This work addresses a foundational problem in AI for applications like fairness and responsibility, but it is incremental as it builds on existing causal modeling approaches.
The paper tackles the problem of evaluating counterfactual statements in AI by addressing counterfactual identification and estimation from observational and experimental data, showing that neural causal models are expressive enough for this task and developing a sound and complete algorithm for it.
Evaluating hypothetical statements about how the world would be had a different course of action been taken is arguably one key capability expected from modern AI systems. Counterfactual reasoning underpins discussions in fairness, the determination of blame and responsibility, credit assignment, and regret. In this paper, we study the evaluation of counterfactual statements through neural models. Specifically, we tackle two causal problems required to make such evaluations, i.e., counterfactual identification and estimation from an arbitrary combination of observational and experimental data. First, we show that neural causal models (NCMs) are expressive enough and encode the structural constraints necessary for performing counterfactual reasoning. Second, we develop an algorithm for simultaneously identifying and estimating counterfactual distributions. We show that this algorithm is sound and complete for deciding counterfactual identification in general settings. Third, considering the practical implications of these results, we introduce a new strategy for modeling NCMs using generative adversarial networks. Simulations corroborate with the proposed methodology.