Skip to yearly menu bar Skip to main content

Workshop: Causal Representation Learning

A Causal Ordering Prior for Unsupervised Representation Learning

Avinash Kori · Pedro Sanchez · Konstantinos Vilouras · Ben Glocker · Sotirios Tsaftaris

Keywords: [ identifiability results ] [ Unsupervised Learning ] [ causal representation learning ]


Unsupervised representation learning with variational inference relies heavily on independence assumptions over latent variables. Causal representation learning (CRL), however, argues that factors of variation in a dataset are, in fact, causally related. Allowing latent variables to be correlated, as a consequence of causal relationships, is more realistic and generalisable. So far, provably identifiable methods rely on: auxiliary information, weak labels, and interventional or even counterfactual data. Inspired by causal discovery with functional causal models, we propose a fully unsupervised representation learning method that considers a data generation process with a latent additive noise model (ANM). We encourage the latent space to follow a causal ordering via loss function based on the Hessian of the latent distribution.

Chat is not available.