Coarsening Causal DAG Models

2026-01-15

AI Summary

In real-world scenarios, constructing fine-grained causal DAGs is often impractical, necessitating effective coarse-graining methods. This work proposes a novel framework for directly learning abstract causal graphs from interventional data without prior knowledge of intervention targets. By establishing a theory of graphical identifiability, designing the first provably consistent learning algorithm, and uncovering the lattice structure inherent in the space of abstractions, the approach enables principled compression of the original causal model. Experiments on both synthetic data and a real physical system—characterized by interactions between light intensity and polarization—demonstrate that the method accurately recovers known ground-truth abstract causal structures.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Directed acyclic graphical (DAG) models are a powerful tool for representing causal relationships among jointly distributed random variables, especially concerning data from across different experimental settings. However, it is not always practical or desirable to estimate a causal model at the granularity of given features in a particular dataset. There is a growing body of research on causal abstraction to address such problems. We contribute to this line of research by (i) providing novel graphical identifiability results for practically-relevant interventional settings, (ii) proposing an efficient, provably consistent algorithm for directly learning abstract causal graphs from interventional data with unknown intervention targets, and (iii) uncovering theoretical insights about the lattice structure of the underlying search space, with connections to the field of causal discovery more generally. As proof of concept, we apply our algorithm on synthetic and real datasets with known ground truths, including measurements from a controlled physical system with interacting light intensity and polarization.

Problem

• causal abstraction
• coarsening
• causal DAG
• interventional data
• causal discovery

Innovation

• causal abstraction
• interventional data
• identifiability
• lattice structure
• causal discovery