提出可识别因果抽象的理论框架，放宽了对干预条件的严格假设。
On the Identifiability of Causal Abstractions
- 基于任意子集的潜在变量干预，推导因果模型可识别程度
- 在更现实的干预条件下，仍能通过抽象层识别系统结构
- 适用于复杂系统中因果推理与可解释性建模的研究者
因果表示学习（CRL）通过学习与数据生成过程相关的结构化因果模型，提升机器学习模型的鲁棒性和泛化能力。本文聚焦一类利用可观测空间中随机未知干预前后对比数据对来识别潜在因果模型的CRL方法。此前研究（Brehmer et al., 2022）表明，在所有潜在变量均可单独干预的前提下，该方法可行，但这一假设在多数系统中过于严格。本文改为假设对潜在变量的任意子集进行干预，更具现实意义。我们构建了一个理论框架，用于计算在给定干预集合下，能够多大程度上识别因果模型，且结果以更高粒度的系统抽象形式呈现。
原文摘要 · Abstract (English)
Causal representation learning (CRL) enhances machine learning models' robustness and generalizability by learning structural causal models associated with data-generating processes. We focus on a family of CRL methods that uses contrastive data pairs in the observable space, generated before and after a random, unknown intervention, to identify the latent causal model. (Brehmer et al., 2022) showed that this is indeed possible, given that all latent variables can be intervened on individually. However, this is a highly restrictive assumption in many systems. In this work, we instead assume interventions on arbitrary subsets of latent variables, which is more realistic. We introduce a theoretical framework that calculates the degree to which we can identify a causal model, given a set of possible interventions, up to an abstraction that describes the system at a higher level of granularity.
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。