Identifying Structural Biases from Causal Mechanism Shifts

2026-06-17

AI Summary

Causal discovery is often hindered by violations of the independent and identically distributed (i.i.d.) assumption or the presence of unobserved variables, leading to confounding and selection bias that are difficult to accurately identify. This work proposes a novel approach that analyzes dependency patterns in the transfer of causal mechanisms across multiple environments to uncover the type of structural bias and the variables it affects. The key innovation lies in establishing a testable criterion based on mutual information, which for the first time enables principled differentiation between confounding and selection bias. Building on this criterion, the authors develop the StruBI algorithm for efficient inference. Experimental results demonstrate that the proposed method significantly outperforms state-of-the-art approaches on both synthetic and real-world datasets, accurately identifying the source of bias and its impacted variables.

Abstract

Causal discovery methods commonly assume that all data is independently and identically distributed (i.i.d.) and that there are no unmeasured variables affecting the system. In practice, these assumptions are often violated, leading to inaccurate inference. In this paper, we study how to identify hidden confounding and selection biases from causal mechanism shifts. In particular, we show that structural biases lead to dependent mechanism shifts. That is, by considering for which variables the mechanisms change given data from different environments, we can tell which variables are unbiased, which are subject to hidden confounding, and which are undergoing selection bias. We formalize this into an empirically testable criterion based on mutual information, and show under which conditions it identifies structural biases. To tell which nodes are subject to what kind of bias, we introduce the StruBI algorithm. Experiments on synthetic and real-world data show that StruBI works well in practice, accurately recovering affected variable sets and types of biases, outperforming the state-of-the-art by a wide margin.

Problem

• structural bias
• causal discovery
• hidden confounding
• selection bias
• mechanism shift

Innovation

• causal mechanism shifts
• structural biases
• hidden confounding
• selection bias
• mutual information