Estimating Categorical Counterfactuals via Deep Twin Networks
원문 초록
Counterfactual inference is a powerful tool, capable of solving challenging problems in high-profile sectors. To perform counterfactual inference, one requires knowledge of the underlying causal mechanisms. However, causal mechanisms cannot be uniquely determined from observations and interventions alone. This raises the question of how to choose the causal mechanisms so that resulting counterfactual inference is trustworthy in a given domain. This question has been addressed in causal models with binary variables, but the case of categorical variables remains unanswered. We address this challenge by introducing for causal models with categorical variables the notion of counterfactual ordering, a principle that posits desirable properties causal mechanisms should posses, and prove that it is equivalent to specific functional constraints on the causal mechanisms. To learn causal mechanisms satisfying these constraints, and perform counterfactual inference with them, we introduce deep twin networks. These are deep neural networks that, when trained, are capable of twin network counterfactual inference -- an alternative to the abduction, action, & prediction method. We empirically test our approach on diverse real-world and semi-synthetic data from medicine, epidemiology, and finance, reporting accurate estimation of counterfactual probabilities while demonstrating the issues that arise with counterfactual reasoning when counterfactual ordering is not enforced.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Active Inference AI Systems for Scientific Discovery
HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation
An introduction to Causal Modelling
Learning Meta-path-aware Embeddings for Recommender Systems
A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models
Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.