We introduce structural causal bottleneck models (SCBMs), a novel class of structural causal models. At the core of SCBMs lies the assumption that causal effects between high-dimensional variables only depend on low-dimensional summary statistics, or bottlenecks, of the causes. SCBMs provide a flexible framework for task-specific dimension reduction while being estimable via standard, simple learning algorithms in practice. We analyse identifiability in SCBMs, connect them to information bottlenecks in the sense of Tishby & Zaslavsky (2015), and illustrate how to estimate them experimentally. We also demonstrate the benefit of bottlenecks for effect estimation in low-sample transfer learning settings. We argue that SCBMs provide an alternative to existing causal dimension reduction frameworks like causal representation learning or causal abstraction learning.

翻译：我们提出了结构因果瓶颈模型（SCBMs），这是一类新型的结构因果模型。SCBMs的核心假设是：高维变量间的因果效应仅取决于其成因的低维汇总统计量，或称瓶颈。SCBMs为任务特定的降维提供了一个灵活的框架，同时在实际中可通过标准、简单的学习算法进行估计。我们分析了SCBMs的可识别性，将其与Tishby & Zaslavsky (2015)意义上的信息瓶颈联系起来，并通过实验说明了如何对其进行估计。我们还展示了在低样本迁移学习场景中，瓶颈对于效应估计的益处。我们认为，SCBMs为现有的因果降维框架（如因果表示学习或因果抽象学习）提供了一种替代方案。