Decoupled Causal Discovery
Abstract
Causal discovery from observational data is a fundamental yet challenging task in scientific research. While existing approaches are primarily based on conditional independence tests, structure scores, or restrictive functional assumptions, we propose Decoupled Causal Discovery (DCD), a novel decoupling-based perspective that does not rely on these methodologies. DCD directly identifies the Markov boundary (MB) by decoupling non-target variables via weighting functions, such that only variables within the MB preserve dependence with the target under the decoupled distribution. Building on this, DCD iteratively constructs the Completed Partially Directed Acyclic Graph (CPDAG) by exploiting structural asymmetries within the MBs. We establish the theoretical identifiability, soundness, and completeness of DCD. Empirical evaluations demonstrate that DCD achieves strong performance, particularly excelling in challenging noise regimes.
Related
- Interpretable Causal Discovery via Causal-Effect Constraints
- sHAIL-Causal: A Sequential Staircase Procedure for Invariant Causal Predictor Discovery
- Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings
- Integrating Background Knowledge for Scalable Causal Discovery
- Causal Discovery via Transformed Low-Rank Quantile Surfaces
BibTeX
@misc{guan2026decoupled,
title = {{Decoupled Causal Discovery}},
author = {Zhengkang Guan and Fei Wu and Kun Kuang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23535},
eprint = {2609.23535},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23535},
}
RIS
TY - UNPB
TI - Decoupled Causal Discovery
AU - Zhengkang Guan
AU - Fei Wu
AU - Kun Kuang
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23535
UR - https://arxiv.org/abs/2609.23535
AB - Causal discovery from observational data is a fundamental yet challenging task in scientific research. While existing approaches are primarily based on conditional independence tests, structure scores, or restrictive functional assumptions, we propose Decoupled Causal Discovery (DCD), a novel decoupling-based perspective that does not rely on these methodologies. DCD directly identifies the Markov boundary (MB) by decoupling non-target variables via weighting functions, such that only variables within the MB preserve dependence with the target under the decoupled distribution. Building on this, DCD iteratively constructs the Completed Partially Directed Acyclic Graph (CPDAG) by exploiting structural asymmetries within the MBs. We establish the theoretical identifiability, soundness, and completeness of DCD. Empirical evaluations demonstrate that DCD achieves strong performance, particularly excelling in challenging noise regimes.
ER -