Semi-Supervised Learning for Deep Causal Generative Models

arXiv:2403.18717v1 Announce Type: new
Abstract: Developing models that can answer questions of the form "How would $x$ change if $y$ had been $z$?" is fundamental for advancing medical image analysis. Training causal generative models that address such counterfactual questions, though, currently requires that all relevant variables have been observed and that corresponding labels are available in training data. However, clinical data may not have complete records for all patients and state of the art causal generative models are unable to …

abstract analysis arxiv causal change counterfactual cs.ai cs.cv cs.lg form generative generative models image labels medical questions semi-supervised semi-supervised learning stat.ml supervised learning training type variables