Identifiable Latent Neural Causal Models

arXiv:2403.15711v1 Announce Type: new
Abstract: Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. It is particularly good at predictions under unseen distribution shifts, because these shifts can generally be interpreted as consequences of interventions. Hence leveraging {seen} distribution shifts becomes a natural strategy to help identifying causal representations, which in turn benefits predictions where distributions are previously {unseen}. Determining the types (or conditions) of such distribution shifts that do contribute to the identifiability of …

abstract arxiv causal consequences cs.lg data distribution good interpreted low natural predictions representation representation learning stat.me stat.ml strategy type