Towards the Reusability and Compositionality of Causal Representations

Davide Talon, Phillip Lippe, Stuart James, Alessio Del Bue, Sara Magliacane

Keywords: Causal Representation Learning, Modularity, Composition

TL;DR: We introduce DECAF, a framework that is a first step towards adapting and composing causal representations.

Abstract:

Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e.g., images. While most CRL works focus on learning causal representations in a single environment, in this work we instead propose a first step towards learning causal representations from temporal sequences of images that can be adapted in a new environment, or composed across multiple related environments. In particular, we introduce DECAF, a framework that detects which causal factors can be reused and which need to be adapted from previously learned causal representations. Our approach is based on the availability of intervention targets, that indicate which variables are perturbed at each time step.
Experiments on three benchmark datasets show that integrating our framework with four state-of-the-art CRL approaches leads to accurate representations in a new environment with only a few samples.

Submission Number: 28