The Library
Jointly learning consistent causal abstractions over multiple interventional distributions
Tools
Zennaro, Fabio Massimo, Drávucz, Máté, Apachitei, Geanina, Widanage, W. Dhammika and Damoulas, Theodoros (2023) Jointly learning consistent causal abstractions over multiple interventional distributions. In: CLeaR (Causal Learning and Reasoning) 2023, Tübingen, Germany, 11-14 Apr 2023. Published in: Proceedings of CLeaR (Causal Learning and Reasoning) 2023 (In Press)
|
PDF
WRAP-Jointly-learning-consistent-causal-abstractions-over-multiple-interventional-distributions-Zennaro-2023.pdf - Accepted Version - Requires a PDF viewer. Download (785Kb) | Preview |
Abstract
An abstraction can be used to relate two structural causal models representing the same system at different levels of resolution. Learning abstractions which guarantee consistency with respect to interventional distributions would allow one to jointly reason about evidence across multiple levels of granularity while respecting the underlying cause-effect relationships. In this paper, we introduce a first framework for causal abstraction learning between SCMs based on the formalization of abstraction recently proposed by Rischel (2020). Based on that, we propose a differentiable programming solution that jointly solves a number of combinatorial sub-problems, and we study its performance and benefits against independent and sequential approaches on synthetic settings and on a challenging real-world problem related to electric vehicle battery manufacturing.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software |
||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science Faculty of Science, Engineering and Medicine > Science > Statistics Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) |
||||||
Library of Congress Subject Headings (LCSH): | Causation -- Mathematical models, Artificial intelligence, Machine learning | ||||||
Journal or Publication Title: | Proceedings of CLeaR (Causal Learning and Reasoning) 2023 | ||||||
Publisher: | Open Review | ||||||
Official Date: | 2023 | ||||||
Dates: |
|
||||||
Status: | Peer Reviewed | ||||||
Publication Status: | In Press | ||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||
Date of first compliant deposit: | 16 January 2023 | ||||||
Date of first compliant Open Access: | 16 January 2023 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | CLeaR (Causal Learning and Reasoning) 2023 | ||||||
Type of Event: | Conference | ||||||
Location of Event: | Tübingen, Germany | ||||||
Date(s) of Event: | 11-14 Apr 2023 | ||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year