EUVIMEDEUVIMED entdecken
Crossref

COGS: A Causal Representation Learning Framework for Out-of-Distribution Generalization in Time Series

Xinxin Song, Yuxiao Cheng, Tingxiong Xiao, Jinli Suo

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (30) · 25572-25580

DOI: 10.1609/aaai.v40i30.39753 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xinxin Song und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Time series analysis is crucial in various fields such as healthcare and finance. However, environmental variations and the inherent non-stationarity of time series data often lead to out-of-distribution (OOD) scenarios, consequently causing model performance degradation. Most existing OOD generalization methods primarily focus on images or text, leaving time series analysis relatively underexplored. In this paper, we propose COGS, a novel framework that incorporates causal representation learning into the OOD generalization of time series. By imposing structural priors, our method identifies latent variables and learns a causal graph to disentangle causal variables from non-causal ones. These causal variables are then used to learn domain-invariant representations for stable prediction. Moreover, to tackle the challenge of the absence of domain labels, we further introduce a prototype-based domain discovery algorithm that infers domain labels in an unsupervised manner. The entire framework is optimized in a two-phase iterative manner, resulting in robust OOD performance. Extensive experiments on multiple real-world time series datasets demonstrate that our method achieves competitive performance compared to baseline methods.

Zitieren

APA

Song, X., Cheng, Y., Xiao, T., & Suo, J. (2026). COGS: A Causal Representation Learning Framework for Out-of-Distribution Generalization in Time Series. Proceedings of the AAAI Conference on Artificial Intelligence, 40(30), 25572-25580. https://doi.org/10.1609/aaai.v40i30.39753

Vancouver

Song X, Cheng Y, Xiao T, Suo J. COGS: A Causal Representation Learning Framework for Out-of-Distribution Generalization in Time Series. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(30):25572-25580. doi:10.1609/aaai.v40i30.39753

BibTeX
@article{Song2026,
  author = {Song, Xinxin and Cheng, Yuxiao and Xiao, Tingxiong and Suo, Jinli},
  title = {COGS: A Causal Representation Learning Framework for Out-of-Distribution Generalization in Time Series},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {30},
  pages = {25572--25580},
  doi = {10.1609/aaai.v40i30.39753}
}
Kostenlos starten →