arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.08682stat.MLcs.LG
收藏

结构因果瓶颈模型

Structural Causal Bottleneck Models

Department of Computer Science, University of Potsdam(波恩大学计算机科学系);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心)

Simon Bing, Jonas Wahl, Jakob Runge

AI总结:

本文提出结构因果瓶颈模型(SCBMs),通过低维摘要统计来捕捉高维变量间的因果效应,提供灵活的降维框架,并展示其在小样本迁移学习中的优势。

摘要:

我们引入了结构因果瓶颈模型(SCBMs),一种新的结构因果模型。SCBMs的核心假设是高维变量间的因果效应仅依赖于因果的低维摘要统计(瓶颈)。SCBMs提供了一个灵活的任务特定降维框架,同时可通过标准简单学习算法进行估计。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,并展示了如何实验性地估计它们。我们还展示了瓶颈在低样本迁移学习中的效用。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替代方案。

英文摘要:

We introduce structural causal bottleneck models (SCBMs), a novel class of structural causal models in which causal effects between high-dimensional variables are mediated by low-dimensional summary statistics, or *bottlenecks*. SCBMs provide a flexible framework for mechanism-specific, target-dependent dimension reduction while remaining estimable via standard learning algorithms. We prove that bottleneck variables are identifiable up to bijection from observational data, and validate this experimentally. We then study causal effect estimation in linear SCBMs under three standard adjustment strategies. For instrumental variables, we identify a population-level non-identifiability of naïve two-stage least squares when all variables are high-dimensional, and show that bottleneck representations restore identification. For mediation and backdoor adjustment, we prove that conditioning on bottleneck variables yields valid effect estimates with explicit finite-sample efficiency gains over conditioning on full high-dimensional variables. We argue that SCBMs provide a principled alternative to existing causal dimension reduction frameworks such as causal representation learning and causal abstractions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑