Causal Abstraction Via Emergence for Predicting Bilateral Trade

Aruna Jammalamadaka, Dana Warmsley, Tsai-Ching Lu
Proceedings of The 2021 Causal Analysis Workshop Series, PMLR 160:39-51, 2021.

Abstract

Causal abstraction is key in finding efficient representations of noisy and complex systems, for decision-making and prediction of future system states. Hand-crafted causal abstractions, although accurate and interpretable, can be costly to construct and cannot generalize to large, novel datasets. In this paper, we explore the information-theoretic concept of causal emergence, its correspondence to recent definitions of causal abstraction, and the properties of emergent representations that enable more accurate state predictions and semantic interpretations. Using the bilateral trade network as a case study, we enumerate the conditions under which trade agreements exhibit causal emergence properties, and show that causally emergent representations are indeed able to provide better prediction capability than original trade network representations in a variety of cases.

Cite this Paper

BibTeX
@InProceedings{pmlr-v160-jammalamadaka21a, title = {Causal Abstraction Via Emergence for Predicting Bilateral Trade}, author = {Jammalamadaka, Aruna and Warmsley, Dana and Lu, Tsai-Ching}, booktitle = {Proceedings of The 2021 Causal Analysis Workshop Series}, pages = {39--51}, year = {2021}, editor = {Ma, Sisi and Kummerfeld, Erich}, volume = {160}, series = {Proceedings of Machine Learning Research}, month = {16 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v160/jammalamadaka21a/jammalamadaka21a.pdf}, url = {https://proceedings.mlr.press/v160/jammalamadaka21a.html}, abstract = {Causal abstraction is key in finding efficient representations of noisy and complex systems, for decision-making and prediction of future system states. Hand-crafted causal abstractions, although accurate and interpretable, can be costly to construct and cannot generalize to large, novel datasets. In this paper, we explore the information-theoretic concept of causal emergence, its correspondence to recent definitions of causal abstraction, and the properties of emergent representations that enable more accurate state predictions and semantic interpretations. Using the bilateral trade network as a case study, we enumerate the conditions under which trade agreements exhibit causal emergence properties, and show that causally emergent representations are indeed able to provide better prediction capability than original trade network representations in a variety of cases.} }
Endnote
%0 Conference Paper %T Causal Abstraction Via Emergence for Predicting Bilateral Trade %A Aruna Jammalamadaka %A Dana Warmsley %A Tsai-Ching Lu %B Proceedings of The 2021 Causal Analysis Workshop Series %C Proceedings of Machine Learning Research %D 2021 %E Sisi Ma %E Erich Kummerfeld %F pmlr-v160-jammalamadaka21a %I PMLR %P 39--51 %U https://proceedings.mlr.press/v160/jammalamadaka21a.html %V 160 %X Causal abstraction is key in finding efficient representations of noisy and complex systems, for decision-making and prediction of future system states. Hand-crafted causal abstractions, although accurate and interpretable, can be costly to construct and cannot generalize to large, novel datasets. In this paper, we explore the information-theoretic concept of causal emergence, its correspondence to recent definitions of causal abstraction, and the properties of emergent representations that enable more accurate state predictions and semantic interpretations. Using the bilateral trade network as a case study, we enumerate the conditions under which trade agreements exhibit causal emergence properties, and show that causally emergent representations are indeed able to provide better prediction capability than original trade network representations in a variety of cases.
APA
Jammalamadaka, A., Warmsley, D. & Lu, T.. (2021). Causal Abstraction Via Emergence for Predicting Bilateral Trade. Proceedings of The 2021 Causal Analysis Workshop Series, in Proceedings of Machine Learning Research 160:39-51 Available from https://proceedings.mlr.press/v160/jammalamadaka21a.html.

Related Material