A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms

TL;DR

This paper introduces a meta-learning approach that leverages the speed of adaptation to identify causal structures and disentangle mechanisms, even under non-stationary conditions and without explicit intervention knowledge.

Contribution

It proposes a novel meta-learning framework that uses adaptation speed to infer causal relationships and learn causal representations in complex, changing environments.

Findings

Faster adaptation indicates correct causal structures.

Causal mechanisms can be learned end-to-end with continuous parameters.

The approach works without explicit intervention labels.

Abstract

We propose to meta-learn causal structures based on how fast a learner adapts to new distributions arising from sparse distributional changes, e.g. due to interventions, actions of agents and other sources of non-stationarities. We show that under this assumption, the correct causal structural choices lead to faster adaptation to modified distributions because the changes are concentrated in one or just a few mechanisms when the learned knowledge is modularized appropriately. This leads to sparse expected gradients and a lower effective number of degrees of freedom needing to be relearned while adapting to the change. It motivates using the speed of adaptation to a modified distribution as a meta-learning objective. We demonstrate how this can be used to determine the cause-effect relationship between two observed variables. The distributional changes do not need to correspond to standard interventions (clamping a variable), and the learner has no direct knowledge of these interventions. We show that causal structures can be parameterized via continuous variables and learned end-to-end. We then explore how these ideas could be used to also learn an encoder that would map low-level observed variables to unobserved causal variables leading to faster adaptation out-of-distribution, learning a representation space where one can satisfy the assumptions of independent mechanisms and of small and sparse changes in these mechanisms due to actions and non-stationarities.