提出因果信息瓶颈，让变量抽象既压缩信息又保留因果关系。
The Causal Information Bottleneck and Optimal Causal Variable Abstractions
- 在传统信息瓶颈基础上引入因果结构，压缩变量时保持对目标变量的因果控制。
- 实验显示学习到的抽象能准确捕捉预期的因果关系。
- 适合需要可解释因果推理的场景，如干预分析和系统建模。
为有效研究复杂因果系统，常需通过丢弃无关细节来构建系统部分的抽象。信息瓶颈（IB）方法广泛用于变量抽象，通过压缩随机变量同时保留对目标变量的预测能力。但传统方法纯属统计，忽略潜在因果结构，难以适用于因果任务。本文提出因果信息瓶颈（CIB），作为IB的因果扩展，可在压缩一组选定变量的同时维持对目标变量的因果控制。该方法生成的抽象具有因果可解释性，揭示抽象变量与目标变量间的相互作用，并可用于干预推理。实验结果表明，所学抽象能准确捕捉预期的因果关系。
原文摘要 · Abstract (English)
To effectively study complex causal systems, it is often useful to construct abstractions of parts of the system by discarding irrelevant details while preserving key features. The Information Bottleneck (IB) method is a widely used approach to construct variable abstractions by compressing random variables while retaining predictive power over a target variable. Traditional methods like IB are purely statistical and ignore underlying causal structures, making them ill-suited for causal tasks. We propose the Causal Information Bottleneck (CIB), a causal extension of the IB, which compresses a set of chosen variables while maintaining causal control over a target variable. This method produces abstractions of (sets of) variables which are causally interpretable, give us insight about the interactions between the abstracted variables and the target variable, and can be used when reasoning about interventions. We present experimental results demonstrating that the learned abstractions accurately capture causal relations as intended.
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。