Multi-View Causal Representation Learning with Partial Observability

arXiv:2311.04056v2 Announce Type: replace
Abstract: We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a nonlinear mixture of a subset of underlying latent variables, which can be causally related. We prove that the information shared across all subsets of any number of views can be learned up to a smooth bijection using contrastive learning and a single …

abstract arxiv cs.ai cs.lg data framework observability representation representation learning studying type variables view