Identifiable Latent Polynomial Causal Models Through the Lens of Change
This work addresses the challenge of causal representation learning for researchers in machine learning and AI, providing theoretical and empirical advances in identifiability for nonlinear models, though it builds incrementally on prior linear methods.
The paper tackles the problem of identifying latent causal models with nonlinear relationships and general noise distributions, extending beyond linear Gaussian assumptions, and demonstrates consistent learning of latent causal representations through both synthetic and real-world experiments.
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability. A recent breakthrough explores identifiability by leveraging the change of causal influences among latent causal variables across multiple environments \citep{liu2022identifying}. However, this progress rests on the assumption that the causal relationships among latent causal variables adhere strictly to linear Gaussian models. In this paper, we extend the scope of latent causal models to involve nonlinear causal relationships, represented by polynomial models, and general noise distributions conforming to the exponential family. Additionally, we investigate the necessity of imposing changes on all causal parameters and present partial identifiability results when part of them remains unchanged. Further, we propose a novel empirical estimation method, grounded in our theoretical finding, that enables learning consistent latent causal representations. Our experimental results, obtained from both synthetic and real-world data, validate our theoretical contributions concerning identifiability and consistency.