Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

arXiv:2406.14302v1 Announce Type: cross
Abstract: Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather independently. We observe that several methods in both representation and causal structure learning rely on the same data-generating process (DGP), namely, exchangeable but not i.i.d. (independent and identically distributed) data. We provide a unified framework, termed Identifiable Exchangeable Mechanisms (IEM), for representation and structure learning under the lens of exchangeability. IEM provides new …

abstract arxiv causal cs.ai cs.lg data fields good however important observe performance process representation representation learning stat.ml type