提出新方法解决反事实推理的可识别性问题，理论更统一且可实证。
Exogenous Isomorphism for Counterfactual Identifiability
- 引入外生同构概念，简化反事实可识别性分析。
- 在两类特殊模型中证明了新识别性的充分条件。
- 适用于需要严格反事实一致性的实际场景，如医疗决策。
本文研究了$ ilde{\sim}_{\mathcal{L}_3}$-可识别性，即皮尔因果层级框架下完全的反事实可识别性，确保所有满足假设的结构因果模型对所有因果问题给出一致答案。为简化此问题，我们引入外生同构，提出$ ilde{\sim}_{\mathrm{EI}}$-可识别性，反映实现$ ilde{\sim}_{\mathcal{L}_3}$-可识别性所需模型辨识强度。我们探讨了在两类特殊结构因果模型（双射模型BSCMs与三角单调模型TM-SCMs）中达成$ ilde{\sim}_{\mathrm{EI}}$-可识别性的充分条件，其中后者扩展了$ ilde{\sim}_{\mathcal{L}_2}$-可识别性。结果统一并推广了现有理论，为实际应用提供理论保障。最后，我们利用神经网络实现的TM-SCMs解决了反事实推理中的不一致性问题，实验验证了方法有效性及理论正确性。
原文摘要 · Abstract (English)
This paper investigates $\sim_{\mathcal{L}_3}$-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 $\sim_{\mathrm{EI}}$-identifiability, reflecting the strength of model identifiability required for $\sim_{\mathcal{L}_3}$-identifiability. We explore sufficient assumptions for achieving $\sim_{\mathrm{EI}}$-identifiability in two special classes of SCMs: Bijective SCMs (BSCMs), based on counterfactual transport, and Triangular Monotonic SCMs (TM-SCMs), which extend $\sim_{\mathcal{L}_2}$-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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。