Disentanglement in Implicit Causal Models via Switch Variable
CoRR(2024)
摘要
Learning causal representations from observational and interventional data in
the absence of known ground-truth graph structures necessitates implicit latent
causal representation learning. Implicitly learning causal mechanisms typically
involves two categories of interventional data: hard and soft interventions. In
real-world scenarios, soft interventions are often more realistic than hard
interventions, as the latter require fully controlled environments. Unlike hard
interventions, which directly force changes in a causal variable, soft
interventions exert influence indirectly by affecting the causal mechanism. In
this paper, we tackle implicit latent causal representation learning in a
Variational Autoencoder (VAE) framework through soft interventions. Our
approach models soft interventions effects by employing a causal mechanism
switch variable designed to toggle between different causal mechanisms. In our
experiments, we consistently observe improved learning of identifiable, causal
representations, compared to baseline approaches.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要