arXiv：cs.LG· Jani Nyk\"anen, Otto Tabell, Santtu Tikka, Juha Karvanen·· 3 小时前AI 评分31
因果效应识别中聚类操作的识别不变性
Invariance of Clustering Operations in Causal Effect Identification
AI 导读
因果图中对变量进行聚类可缩小图规模、简化因果推断，但任意聚类会改变变量间的关键因果关系并导致错误结论。研究者提出了一类基于原图 c-components 条件的聚类操作，当可识别性与不可识别性均被保留时，该聚类操作被称为识别不变（identification invariant），并展示了其在实际场景中的应用。
正文
Abstract:Clustering variables in causal graphs reduces the size of the graph and simplifies causal inference. However, arbitrary clustering can alter crucial causal relations among variables and lead to erroneous conclusions. While the identifiability of a causal effect in the clustered graph implies the identifiability in the original graph under mild conditions, nonidentifiability in clustered graph does not imply nonidentifiability in the original graph without further assumptions. When both identifiability and nonidentifiability are preserved, the clustering operation is called identification invariant. We present a broad class of clustering operations that are identification invariant based on conditions related to the c-components of the original graph. Finally, we demonstrate use of the results in practical settings.
| Subjects: | Machine Learning (stat.ML); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03101 [stat.ML] |
| (or arXiv:2610.03101v1 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03101 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jani Nykänen [view email]
[v1]
Fri, 2 Oct 2026 10:22:38 UTC (33 KB)
来源：arXiv：cs.LG · arxiv.org