提出可抵御分布变化的因果抽象方法，提升模型鲁棒性。
Distributionally Robust Causal Abstractions
- 用Wasserstein不确定集构建对抗性优化框架，增强对分布偏移的抵抗力
- 理论证明在真实与高斯环境中均能控制最坏情况下的抽象误差
- 适用于需要稳定因果推理的场景，如医疗、自动驾驶等
因果抽象（CA）理论为不同粒度层级的因果模型提供了一致的关联框架，确保干预一致性。然而，现有学习方法依赖固定且准确的外生分布假设，易受环境变化和模型误设影响。本文首次提出分布鲁棒型因果抽象及其学习算法，将鲁棒抽象学习建模为带Wasserstein不确定集的约束极小极大优化问题。在经验环境与高斯环境下提供了理论保证，支持不确定集半径的合理选择，并给出最坏情况抽象误差的量化控制。此外，通过多种任务与学习方法的实证验证，表明该框架不仅能应对环境漂移，还可抵御结构与干预映射误设的影响。
原文摘要 · Abstract (English)
Causal Abstraction (CA) theory provides a principled framework for relating causal models that describe the same system at different levels of granularity while ensuring interventional consistency between them. Recent methods for learning CAs, however, assume fixed and well-specified exogenous distributions, leaving them vulnerable to environmental shifts and model misspecification. In this work, we address these limitations by introducing the first class of distributionally robust CAs and their associated learning algorithms. The latter cast robust causal abstraction learning as a constrained min-max optimization problem with Wasserstein ambiguity sets. We provide theoretical guarantees for both empirical and Gaussian environments, enabling principled selection of ambiguity set radii and establish quantitative guarantees on worst-case abstraction error. Furthermore, we present empirical evidence across different problems and CA learning methods, demonstrating our framework's robustness not only to environmental shifts but also to structural and intervention mapping misspecification.
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。