Identifying general mechanism shifts in linear causal representations

Chen T, Bello K, Locatello F, Aragam B, Ravikumar PK. 2024. Identifying general mechanism shifts in linear causal representations. 38th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, NeurIPS, vol. 38.

Download
OA 2024_NeurIPS_Chen.pdf 5.66 MB [Published Version]
Conference Paper | Published | English
Author
Chen, Tianyu; Bello, Kevin; Locatello, FrancescoISTA ; Aragam, Bryon; Ravikumar, Pradeep Kumar
Department
Series Title
NeurIPS
Abstract
We consider the linear causal representation learning setting where we observe a linear mixing of d unknown latent factors, which follow a linear structural causal model. Recent work has shown that it is possible to recover the latent factors as well as the underlying structural causal model over them, up to permutation and scaling, provided that we have at least d environments, each of which corresponds to perfect interventions on a single latent node (factor). After this powerful result, a key open problem faced by the community has been to relax these conditions: allow for coarser than perfect single-node interventions, and allow for fewer than d of them, since the number of latent factors d could be very large. In this work, we consider precisely such a setting, where we allow a smaller than d number of environments, and also allow for very coarse interventions that can very coarsely \textit{change the entire causal graph over the latent factors}. On the flip side, we relax what we wish to extract to simply the \textit{list of nodes that have shifted between one or more environments}. We provide a surprising identifiability result that it is indeed possible, under some very mild standard assumptions, to identify the set of shifted nodes. Our identifiability proof moreover is a constructive one: we explicitly provide necessary and sufficient conditions for a node to be a shifted node, and show that we can check these conditions given observed data. Our algorithm lends itself very naturally to the sample setting where instead of just interventional distributions, we are provided datasets of samples from each of these distributions. We corroborate our results on both synthetic experiments as well as an interesting psychometric dataset. The code can be found at https://github.com/TianyuCodings/iLCS.
Publishing Year
Date Published
2024-09-25
Proceedings Title
38th Conference on Neural Information Processing Systems
Publisher
Curran Associates
Volume
38
Conference
NeurIPS: Neural Information Processing Systems
Conference Location
Vancouver, Canada
Conference Date
2024-12-16 – 2024-12-16
IST-REx-ID

Cite this

Chen T, Bello K, Locatello F, Aragam B, Ravikumar PK. Identifying general mechanism shifts in linear causal representations. In: 38th Conference on Neural Information Processing Systems. Vol 38. Curran Associates; 2024.
Chen, T., Bello, K., Locatello, F., Aragam, B., & Ravikumar, P. K. (2024). Identifying general mechanism shifts in linear causal representations. In 38th Conference on Neural Information Processing Systems (Vol. 38). Vancouver, Canada: Curran Associates.
Chen, Tianyu, Kevin Bello, Francesco Locatello, Bryon Aragam, and Pradeep Kumar Ravikumar. “Identifying General Mechanism Shifts in Linear Causal Representations.” In 38th Conference on Neural Information Processing Systems, Vol. 38. Curran Associates, 2024.
T. Chen, K. Bello, F. Locatello, B. Aragam, and P. K. Ravikumar, “Identifying general mechanism shifts in linear causal representations,” in 38th Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 38.
Chen T, Bello K, Locatello F, Aragam B, Ravikumar PK. 2024. Identifying general mechanism shifts in linear causal representations. 38th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, NeurIPS, vol. 38.
Chen, Tianyu, et al. “Identifying General Mechanism Shifts in Linear Causal Representations.” 38th Conference on Neural Information Processing Systems, vol. 38, Curran Associates, 2024.
All files available under the following license(s):
Creative Commons Attribution 4.0 International Public License (CC-BY 4.0):
Main File(s)
File Name
Access Level
OA Open Access
Date Uploaded
2025-02-04
MD5 Checksum
75c3091e70bd2916cd94afbf40a0c425


Export

Marked Publications

Open Data ISTA Research Explorer

Sources

arXiv 2410.24059

Search this title in

Google Scholar