The Library
Causal optimal transport of abstractions
Tools
Felekis, Yorgos, Zennaro, Fabio Massimo, Branchini, Nicola and Damoulas, Theodoros (2024) Causal optimal transport of abstractions. In: CLeaR (Causal Learning and Reasoning) 2024, Los Angeles, California, 01-03 Apr 2024. Published in: Proceedings of the Third Conference on Causal Learning and Reasoning, 236 pp. 462-498. ISSN 2640-3498.
|
PDF
WRAP-causal-optimal-transport-abstractions-Felekis-2024.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (1120Kb) | Preview |
|
PDF
WRAP-Causal-optimal-transport-abstractions-24.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only - Requires a PDF viewer. Download (1261Kb) |
Official URL: https://proceedings.mlr.press/v236/felekis24a.html
Abstract
Causal abstraction (CA) theory establishes formal criteria for relating multiple structural causal models (SCMs) at different levels of granularity by defining maps between them. These maps have significant relevance for real-world challenges such as synthesizing causal evidence from multiple experimental environments, learning causally consistent representations at different resolutions, and linking interventions across multiple SCMs. In this work, we propose COTA, the first method to learn abstraction maps from observational and interventional data without assuming complete knowledge of the underlying SCMs. In particular, we introduce a multi-marginal Optimal Transport (OT) formulation that enforces do-calculus causal constraints, together with a cost function that relies on interventional information. We extensively evaluate COTA on synthetic and real world problems, and showcase its advantages over non-causal, independent and aggregated OT formulations. Finally, we demonstrate the efficiency of our method as a data augmentation tool by comparing it against prior art of CA learning, which assumes fully specified SCMs, on a real-world downstream task.
Item Type: | Conference Item (Paper) | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||||||||
Series Name: | Proceedings of Machine Learning Research | ||||||||||||
Journal or Publication Title: | Proceedings of the Third Conference on Causal Learning and Reasoning | ||||||||||||
Publisher: | PMLR ; MLResearchPress | ||||||||||||
ISSN: | 2640-3498 | ||||||||||||
Official Date: | 2024 | ||||||||||||
Dates: |
|
||||||||||||
Volume: | 236 | ||||||||||||
Page Range: | pp. 462-498 | ||||||||||||
Status: | Peer Reviewed | ||||||||||||
Publication Status: | Published | ||||||||||||
Access rights to Published version: | Free Access (unspecified licence, 'bronze OA') | ||||||||||||
Date of first compliant deposit: | 24 January 2024 | ||||||||||||
Date of first compliant Open Access: | 9 May 2024 | ||||||||||||
RIOXX Funder/Project Grant: |
|
||||||||||||
Conference Paper Type: | Paper | ||||||||||||
Title of Event: | CLeaR (Causal Learning and Reasoning) 2024 | ||||||||||||
Type of Event: | Conference | ||||||||||||
Location of Event: | Los Angeles, California | ||||||||||||
Date(s) of Event: | 01-03 Apr 2024 | ||||||||||||
Related URLs: | |||||||||||||
Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year