Continual Causal Abstractions

Matej Zečević, Moritz Willig, Florian Peter Busch, Jonas Seng
Proceedings of The First AAAI Bridge Program on Continual Causality, PMLR 208:45-51, 2023.

Abstract

This short paper discusses continually updated causal abstractions as a potential direction of future research. The key idea is to revise the existing level of causal abstraction to a different level of detail that is both consistent with the history of observed data and more effective in solving a given task.

Cite this Paper

BibTeX
@InProceedings{pmlr-v208-zecevic23a, title = {Continual Causal Abstractions}, author = {Ze\v{c}evi\'c, Matej and Willig, Moritz and Busch, Florian Peter and Seng, Jonas}, booktitle = {Proceedings of The First AAAI Bridge Program on Continual Causality}, pages = {45--51}, year = {2023}, editor = {Mundt, Martin and Cooper, Keiland W. and Dhami, Devendra Singh and Ribeiro, Adéle and Smith, James Seale and Bellot, Alexis and Hayes, Tyler}, volume = {208}, series = {Proceedings of Machine Learning Research}, month = {07--08 Feb}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v208/zecevic23a/zecevic23a.pdf}, url = {https://proceedings.mlr.press/v208/zecevic23a.html}, abstract = {This short paper discusses continually updated causal abstractions as a potential direction of future research. The key idea is to revise the existing level of causal abstraction to a different level of detail that is both consistent with the history of observed data and more effective in solving a given task.} }
Endnote
%0 Conference Paper %T Continual Causal Abstractions %A Matej Zečević %A Moritz Willig %A Florian Peter Busch %A Jonas Seng %B Proceedings of The First AAAI Bridge Program on Continual Causality %C Proceedings of Machine Learning Research %D 2023 %E Martin Mundt %E Keiland W. Cooper %E Devendra Singh Dhami %E Adéle Ribeiro %E James Seale Smith %E Alexis Bellot %E Tyler Hayes %F pmlr-v208-zecevic23a %I PMLR %P 45--51 %U https://proceedings.mlr.press/v208/zecevic23a.html %V 208 %X This short paper discusses continually updated causal abstractions as a potential direction of future research. The key idea is to revise the existing level of causal abstraction to a different level of detail that is both consistent with the history of observed data and more effective in solving a given task.
APA
Zečević, M., Willig, M., Busch, F.P. & Seng, J.. (2023). Continual Causal Abstractions. Proceedings of The First AAAI Bridge Program on Continual Causality, in Proceedings of Machine Learning Research 208:45-51 Available from https://proceedings.mlr.press/v208/zecevic23a.html.

Related Material