Prediction under Latent Subgroup Shifts with High-Dimensional Observations
This addresses the challenge of scaling latent-shift adaptation to high-dimensional data like images, which is incremental as it builds on existing RPM frameworks.
The paper tackles the problem of prediction under latent subgroup shifts with high-dimensional observations by introducing a recognition-parametrised model (RPM) to recover low-dimensional, discrete latents from images, enabling adaptation to target environments where previous methods fail to scale.
We introduce a new approach to prediction in graphical models with latent-shift adaptation, i.e., where source and target environments differ in the distribution of an unobserved confounding latent variable. Previous work has shown that as long as "concept" and "proxy" variables with appropriate dependence are observed in the source environment, the latent-associated distributional changes can be identified, and target predictions adapted accurately. However, practical estimation methods do not scale well when the observations are complex and high-dimensional, even if the confounding latent is categorical. Here we build upon a recently proposed probabilistic unsupervised learning framework, the recognition-parametrised model (RPM), to recover low-dimensional, discrete latents from image observations. Applied to the problem of latent shifts, our novel form of RPM identifies causal latent structure in the source environment, and adapts properly to predict in the target. We demonstrate results in settings where predictor and proxy are high-dimensional images, a context to which previous methods fail to scale.