Modern machine learning approaches excel in static settings where a large amount of i.i.d. training data are available for a given task. In a dynamic environment, though, an intelligent agent needs to be able to transfer knowledge and re-use learned components across domains. It has been argued that this may be possible through causal models, aiming to mirror the modularity of the real world in terms of independent causal mechanisms. However, the true causal structure underlying a given set of data is generally not identifiable, so it is desirable to have means to quantify differences between models (e.g., between the ground truth and an estimate), on both the observational and interventional level. In the present work, we introduce the Interventional Kullback-Leibler (IKL) divergence to quantify both structural and distributional differences between models based on a finite set of multi-environment distributions generated by interventions from the ground truth. Since we generally cannot quantify all differences between causal models for every finite set of interventional distributions, we propose a sufficient condition on the intervention targets to identify subsets of observed variables on which the models provably agree or disagree.

翻译：现代机器学习方法在静态环境中表现出色，即针对特定任务可获得大量独立同分布训练数据。然而在动态环境中，智能体需要具备跨领域迁移知识与复用已学习组件的能力。有观点认为，通过因果模型（旨在以独立因果机制映射真实世界的模块化特性）可实现这一目标。但由于给定数据集的真实因果结构通常不可识别，因此有必要建立能同时从观察层面和干预层面量化模型差异（如真实分布与估计分布之间的差异）的手段。本研究提出干预性Kullback-Leibler（IKL）散度，用于基于真实因果机制通过干预产生的有限多环境分布集合，量化因果模型间的结构与分布差异。鉴于我们通常无法通过任意有限干预分布集合完全量化因果模型间的所有差异，我们提出干预目标需满足的充分条件，以识别各模型必然一致或不一致的观测变量子集。