arXiv cs.AI· Danru Xu, Aapo Hyv\"arinen, Sara Magliacane·· 12 小时前AI 评分24
LinADMG：用多域可识别表示学习实现含隐混杂的线性模型因果发现
Causal Discovery for Linear Models with Latent Confounding via Multi-domain Identifiable Representation Learning
AI 导读
研究者提出 LinADMG 框架，通过多域可识别表示学习为含隐混杂的线性因果模型学习 ADMG，不依赖非高斯性或 bow-freeness 假设。该框架证明噪声变量的可识别性足以恢复全部直接因果关系，并在额外的隐混杂无抵消条件下识别完整 ADMG。LinADMG 用四种现有可识别表示学习方法实现，并在模拟与半合成数据集上完成验证。
正文 · 原文
Abstract:Causal discovery with latent confounding is particularly challenging, but a common setting in real-world data. In this work, we focus on linear causal models with latent confounding, represented by acyclic directed mixed graphs (ADMGs). Existing methods that fully identify ADMGs typically assume non-Gaussianity or graphical constraints, such as bow-freeness. In contrast, we propose Linear ADMG Learning (LinADMG), a framework for learning ADMGs for linear causal models through identifiable representation learning. Rather than relying on non-Gaussianity or bow-freeness, LinADMG leverages multi-domain settings to identify the noise variables. We show that the identifiability of the noise variables is sufficient for recovering all direct causal relations, and that, under an additional latent-confounding no-cancellation condition, LinADMG can identify the whole ADMG. We implement LinADMG with four identifiable representation learning approaches from the literature and validate the methods on simulated and semisynthetic datasets.
| Comments: | 29 pages, 6 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28134 [cs.LG] |
| (or arXiv:2610.28134v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28134 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Danru Xu [view email]
[v1]
Tue, 20 Oct 2026 12:43:23 UTC (241 KB)
来源：arXiv cs.AI · arxiv.org