Cluster-Dags as Powerful Background Knowledge For Causal Discovery
cs.LG, cs.AI, stat.ML
Submitted: 2025-12-10
Updated: 2026-08-26
Comments: 23 pages, 5 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Finding cause-effect relationships is of key importance in science.
Terminology
Abstract
Finding cause-effect relationships is of key importance in science. Causal discovery aims to recover a graph from data that succinctly describes these cause-effect relationships. However, current methods face several challenges, especially when dealing with high-dimensional data and complex dependencies. Incorporating prior knowledge about the system can aid causal discovery. In this work, we leverage Cluster-DAGs as a prior knowledge framework to warm-start causal discovery. We show that Cluster-DAGs offer greater flexibility than existing approaches based on tiered background knowledge and introduce two modified constraint-based algorithms, Cluster-PC and Cluster-FCI, for causal discovery in the fully and partially observed setting, respectively. Empirical evaluation on simulated data demonstrates that Cluster-PC and Cluster-FCI outperform their respective baselines without prior knowledge.
Sources
- Evaluation of Induced Expert Knowledge in Causal Structure Learning by NOTEARS
- Average Controlled and Average Natural Micro Direct Effects in Summary Causal Graphs
- Optimizing Data-driven Causal Discovery Using Knowledge-guided Search
- Domain Knowledge in A*-Based Causal Discovery
- Foundation Models for Causal Inference via Prior-Data Fitted Networks
- Causal discovery on vector-valued variables and consistency-guided aggregation
- Clustering and Pruning in Causal Data Fusion
- Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clustering
- Identifiability by common backdoor in summary causal graphs of time series
- Identifiability in Causal Abstractions: A Hierarchy of Criteria
- Causal DAG Summarization (Full Version)
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks