Learning Independent Causal Mechanisms

by   Giambattista Parascandolo, et al.

Independent causal mechanisms are a central concept in the study of causality with implications for machine learning tasks. In this work we develop an algorithm to recover a set of (inverse) independent mechanisms relating a distribution transformed by the mechanisms to a reference distribution. The approach is fully unsupervised and based on a set of experts that compete for data to specialize and extract the mechanisms. We test and analyze the proposed method on a series of experiments based on image transformations. Each expert successfully maps a subset of the transformed data to the original domain, and the learned mechanisms generalize to other domains. We discuss implications for domain transfer and links to recent trends in generative modeling.


Causality Inspired Representation Learning for Domain Generalization

Domain generalization (DG) is essentially an out-of-distribution problem...

A theory of independent mechanisms for extrapolation in generative models

Deep generative models reproduce complex empirical data but cannot extra...

Out-of-distribution Generalization with Causal Invariant Transformations

In real-world applications, it is important and desirable to learn a mod...

Causal Domain Adaptation with Copula Entropy based Conditional Independence Test

Domain Adaptation (DA) is a typical problem in machine learning that aim...

Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning in NLP

The principle of independent causal mechanisms (ICM) states that generat...

Ab initio Algorithmic Causal Deconvolution of Intertwined Programs and Networks by Generative Mechanism

To extract and learn representations leading to generative mechanisms fr...