2022-06-28-wang22b.md

abstract	booktitle	title	year	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Among the most effective methods for uncovering high dimensional unstructured data’s generating mechanisms are techniques based on disentangling and learning independent causal mechanisms. However, to identify the disentangled model, previous methods need additional observable variables or do not provide identifiability results. In contrast, this work aims to design an identifiable generative model that approximates the underlying mechanisms from observational data using only self-supervision. Specifically, the generative model uses a degenerate mixture prior to learn mechanisms that generate or transform data. We outline sufficient conditions for an identifiable generative model up to three types of transformations that preserve a coarse-grained disentanglement. Moreover, we propose a self-supervised training method based on these identifiability conditions. We validate our approach on MNIST, FashionMNIST, and Sprites datasets, showing that the proposed method identifies disentangled models – by visualization and evaluating the downstream predictive model’s accuracy under environment shifts.	First Conference on Causal Learning and Reasoning	Identifying Coarse-grained Independent Causal Mechanisms with Self-supervision	2022	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	wang22b	0	Identifying Coarse-grained Independent Causal Mechanisms with Self-supervision	877	903	877-903	877	false	Wang, Xiaoyang and Nahrstedt, Klara and Koyejo, Oluwasanmi O	given family Xiaoyang Wang given family Klara Nahrstedt given family Oluwasanmi O Koyejo	2022-06-28		Proceedings of the First Conference on Causal Learning and Reasoning	177	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v177/wang22b/wang22b.pdf