Group invariance principles for causal generative models

Abstract

The postulate of independence of cause and mechanism (ICM) has recently led to several new causal discovery algorithms. The interpretation of independence and the way it is utilized, however, varies across these methods. Our aim in this paper is to propose a group theoretic framework for ICM to unify and generalize these approaches. In our setting, the cause-mechanism relationship is assessed by comparing it against a null hypothesis through the application of random generic group transformations. We show that the group theoretic view provides a very general tool to study the structure of data generating mechanisms with direct applications to machine learning.

arXiv comment16 pages, 6 figures

Cited by in corpus (10)

• Causality for Machine Learning
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Counterfactuals uncover the modular structure of deep generative models
• Size-Invariant Graph Representations for Graph Classification Extrapolations
• Causal Adversarial Network for Learning Conditional and Interventional Distributions
• Causal learning with sufficient statistics: an information bottleneck approach
• Independent mechanism analysis, a new concept?
• Neural Networks for Learning Counterfactual G-Invariances from Single Environments
• On Open-Universe Causal Reasoning
• Cause-effect inference through spectral independence in linear dynamical systems: theoretical foundations