Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

intervention inference

Intervention inference is the process of identifying which variables or components in a system have been manipulated, along with the nature of those changes, based on observed data. In causal representation learning and causal discovery, it involves analyzing differences between states or paired samples before and after an unknown manipulation to determine the underlying causal factors that were perturbed. Inferring these intervention targets without explicit supervision enables models to isolate distinct causal variables, reconstruct the latent causal structure of a system, and predict the outcomes of actions in complex environments.

1 item

Weakly supervised causal representation learning

Weakly supervised causal representation learning

Johann Brehmer, Pim de Haan, Phillip Lippe, Taco S. Cohen

OrganizationsQualcommQUVA LabUniversity of Amsterdam

Why you should read this

Proves that high-level causal variables and mechanisms can be identified from pixel-level data paired across unknown interventions, and introduces implicit latent causal models to learn these structures without optimizing discrete graphs.

Learning high-level causal representations together with a causal model from unstructured low-level data such as pixels is impossible from observational data alone. We prove under mild assumptions that this representation is however identifiable in a weakly supervised setting. This involves a dataset with paired samples before and after random, unknown interventions, but no further labels. We then introduce implicit latent causal models, variational autoencoders that represent causal variables and causal structure without having to optimize an explicit discrete graph structure. On simple image data, including a novel dataset of simulated robotic manipulation, we demonstrate that such models can reliably identify the causal structure and disentangle causal variables.

Added

2026-09-30