Identifying Representations for Intervention Extrapolation

arXiv:2310.04295v2 Announce Type: replace
Abstract: The premise of identifiable and causal representation learning is to improve the current representation learning paradigm in terms of generalizability or robustness. Despite recent progress in questions of identifiability, more theoretical results demonstrating concrete advantages of these methods for downstream tasks are needed. In this paper, we consider the task of intervention extrapolation: predicting how interventions affect an outcome, even when those interventions are not observed at training time, and show that identifiable representations can …

abstract advantages arxiv concrete cs.ai cs.lg current paper paradigm progress questions representation representation learning results robustness stat.ml tasks terms type