Causally Inspired Regularization Enables Domain General Representations

Olawale Salaudeen, Sanmi Koyejo
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:3124-3132, 2024.

Abstract

Given a causal graph representing the data-generating process shared across different domains/distributions, enforcing sufficient graph-implied conditional independencies can identify domain-general (non-spurious) feature representations. For the standard input-output predictive setting, we categorize the set of graphs considered in the literature into two distinct groups: (i) those in which the empirical risk minimizer across training domains gives domain-general representations and (ii) those where it does not. For the latter case (ii), we propose a novel framework with regularizations, which we demonstrate are sufficient for identifying domain-general feature representations without a priori knowledge (or proxies) of the spurious features. Empirically, our proposed method is effective for both (semi) synthetic and real-world data, outperforming other state-of-the-art methods in average and worst-domain transfer accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-salaudeen24a, title = { Causally Inspired Regularization Enables Domain General Representations }, author = {Salaudeen, Olawale and Koyejo, Sanmi}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {3124--3132}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/salaudeen24a/salaudeen24a.pdf}, url = {https://proceedings.mlr.press/v238/salaudeen24a.html}, abstract = { Given a causal graph representing the data-generating process shared across different domains/distributions, enforcing sufficient graph-implied conditional independencies can identify domain-general (non-spurious) feature representations. For the standard input-output predictive setting, we categorize the set of graphs considered in the literature into two distinct groups: (i) those in which the empirical risk minimizer across training domains gives domain-general representations and (ii) those where it does not. For the latter case (ii), we propose a novel framework with regularizations, which we demonstrate are sufficient for identifying domain-general feature representations without a priori knowledge (or proxies) of the spurious features. Empirically, our proposed method is effective for both (semi) synthetic and real-world data, outperforming other state-of-the-art methods in average and worst-domain transfer accuracy. } }
Endnote
%0 Conference Paper %T Causally Inspired Regularization Enables Domain General Representations %A Olawale Salaudeen %A Sanmi Koyejo %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-salaudeen24a %I PMLR %P 3124--3132 %U https://proceedings.mlr.press/v238/salaudeen24a.html %V 238 %X Given a causal graph representing the data-generating process shared across different domains/distributions, enforcing sufficient graph-implied conditional independencies can identify domain-general (non-spurious) feature representations. For the standard input-output predictive setting, we categorize the set of graphs considered in the literature into two distinct groups: (i) those in which the empirical risk minimizer across training domains gives domain-general representations and (ii) those where it does not. For the latter case (ii), we propose a novel framework with regularizations, which we demonstrate are sufficient for identifying domain-general feature representations without a priori knowledge (or proxies) of the spurious features. Empirically, our proposed method is effective for both (semi) synthetic and real-world data, outperforming other state-of-the-art methods in average and worst-domain transfer accuracy.
APA
Salaudeen, O. & Koyejo, S.. (2024). Causally Inspired Regularization Enables Domain General Representations . Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:3124-3132 Available from https://proceedings.mlr.press/v238/salaudeen24a.html.

Related Material