Identifying Coarse-grained Independent Causal Mechanisms with Self-supervision

Xiaoyang Wang, Klara Nahrstedt, Oluwasanmi O Koyejo

Keywords: Causal Mechanisms, Identifiability, Disentangled Representations

Abstract: Current approaches for learning disentangled representations assume that independent latent variables generate the data through a single data generation process. In contrast, this manuscript considers independent causal mechanisms (ICM), which, unlike disentangled representations, directly model multiple data generation processes (mechanisms) in a coarse granularity. In this work, we aim to learn a model that disentangles each mechanism and approximates the ground-truth mechanisms from observational data. We outline sufficient conditions under which the mechanisms can be learned using a single self-supervised generative model with an unconventional mixture prior, simplifying previous methods. Moreover, we prove the identifiability of our model w.r.t. the mechanisms in the self-supervised scenario. We compare our approach to disentangled representations on various downstream tasks, showing that our approach is more robust to intervention, covariant shift, and noise due to the disentanglement between the data generation processes.

One-sentence Summary: We propose a self-supervised method to learn the independent causal mechanisms and prove the identifiability.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=R8IGx-kMJI