Towards the Reusability and Compositionality of Causal Representations

arXiv:2403.09830v1 Announce Type: new
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 …

abstract arxiv causal cs.ai cs.lg environment focus images relationships representation representation learning temporal type work