EUVIMEDEUVIMED entdecken
Crossref

Time Series Contrastive Learning with Information-Aware Augmentations

Dongsheng Luo, Wei Cheng, Yingheng Wang, Dongkuan Xu, Jingchao Ni, Wenchao Yu, Xuchao Zhang, Yanchi Liu, Yuncong Chen, Haifeng Chen, Xiang Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (4) · 4534-4542

DOI: 10.1609/aaai.v37i4.25575 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Dongsheng Luo und 10 weiteren Autor:innen. Die Arbeit wurde bisher 107-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key component of contrastive learning is to select appropriate augmentations imposing some priors to construct feasible positive samples, such that an encoder can be trained to learn robust and discriminative representations. Unlike image and language domains where "desired'' augmented samples can be generated with the rule of thumb guided by prefabricated human priors, the ad-hoc manual selection of time series augmentations is hindered by their diverse and human-unrecognizable temporal structures. How to find the desired augmentations of time series data that are meaningful for given contrastive learning tasks and datasets remains an open question. In this work, we address the problem by encouraging both high fidelity and variety based on information theory. A theoretical analysis leads to the criteria for selecting feasible data augmentations. On top of that, we propose a new contrastive learning approach with information-aware augmentations, InfoTS, that adaptively selects optimal augmentations for time series representation learning. Experiments on various datasets show highly competitive performance with up to a 12.0% reduction in MSE on forecasting tasks and up to 3.7% relative improvement in accuracy on classification tasks over the leading baselines.

Zitieren

APA

Luo, D., Cheng, W., Wang, Y., Xu, D., Ni, J., Yu, W., Zhang, X., Liu, Y., Chen, Y., Chen, H., & Zhang, X. (2023). Time Series Contrastive Learning with Information-Aware Augmentations. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4534-4542. https://doi.org/10.1609/aaai.v37i4.25575

Vancouver

Luo D, Cheng W, Wang Y, Xu D, Ni J, Yu W, et al. Time Series Contrastive Learning with Information-Aware Augmentations. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(4):4534-4542. doi:10.1609/aaai.v37i4.25575

BibTeX
@article{Luo2023,
  author = {Luo, Dongsheng and Cheng, Wei and Wang, Yingheng and Xu, Dongkuan and Ni, Jingchao and Yu, Wenchao and Zhang, Xuchao and Liu, Yanchi and Chen, Yuncong and Chen, Haifeng and Zhang, Xiang},
  title = {Time Series Contrastive Learning with Information-Aware Augmentations},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {4},
  pages = {4534--4542},
  doi = {10.1609/aaai.v37i4.25575}
}
Kostenlos starten →