Causal Graph Learning via Distributional Invariance of Cause-Effect Relationship

2026-02-03

Trans. Mach. Learn. Res.

AI Summary

This work addresses the challenge of efficiently and accurately recovering causal graph structures from observational data by proposing a distributional invariance–based causal discovery method. Leveraging the invariance of conditional distributions of causal effects across different environments or prior shifts, the approach identifies causal relationships through stability tests over multiple resampled subsets. It further incorporates sparsity assumptions of the underlying causal graph to design a quadratic-complexity optimization algorithm. The proposed method substantially reduces computational overhead, achieving up to a 25-fold speedup on large-scale benchmark datasets while maintaining accuracy comparable to or better than state-of-the-art approaches, thereby significantly enhancing the scalability of causal discovery.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

This paper introduces a new framework for recovering causal graphs from observational data, leveraging the observation that the distribution of an effect, conditioned on its causes, remains invariant to changes in the prior distribution of those causes. This insight enables a direct test for potential causal relationships by checking the variance of their corresponding effect-cause conditional distributions across multiple downsampled subsets of the data. These subsets are selected to reflect different prior cause distributions, while preserving the effect-cause conditional relationships. Using this invariance test and exploiting an (empirical) sparsity of most causal graphs, we develop an algorithm that efficiently uncovers causal relationships with quadratic complexity in the number of observational variables, reducing the processing time by up to 25x compared to state-of-the-art methods. Our empirical experiments on a varied benchmark of large-scale datasets show superior or equivalent performance compared to existing works, while achieving enhanced scalability.

Problem

• causal graph learning
• observational data
• cause-effect relationship
• distributional invariance

Innovation

• causal graph learning
• distributional invariance
• conditional distribution
• causal discovery
• scalable algorithm