EUVIMEDEUVIMED entdecken
Open Access

CALDA: Improving Multi-Source Time Series Domain Adaptation With Contrastive Adversarial Learning

Garrett Wilson, Janardhan Rao Doppa, Diane J Cook

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-12 · 45 (12) · 14208-14221

DOI: 10.1109/tpami.2023.3298346 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-12. Verfasst von Garrett Wilson und 2 weiteren Autor:innen. Die Arbeit wurde bisher 56-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, NIBIB NIH HHS, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsupervised domain adaptation (UDA) provides a strategy for improving machine learning performance in data-rich (target) domains where ground truth labels are inaccessible but can be found in related (source) domains. In cases where meta-domain information such as label distributions is available, weak supervision can further boost performance. We propose a novel framework, CALDA, to tackle these two problems. CALDA synergistically combines the principles of contrastive learning and adversarial learning to robustly support multi-source UDA (MS-UDA) for time series data. Similar to prior methods, CALDA utilizes adversarial learning to align source and target feature representations. Unlike prior approaches, CALDA additionally leverages cross-source label information across domains. CALDA pulls examples with the same label close to each other, while pushing apart examples with different labels, reshaping the space through contrastive learning. Unlike prior contrastive adaptation methods, CALDA requires neither data augmentation nor pseudo labeling, which may be more challenging for time series. We empirically validate our proposed approach. Based on results from human activity recognition, electromyography, and synthetic datasets, we find utilizing cross-source information improves performance over prior time series and contrastive methods. Weak supervision further improves performance, even in the presence of noise, allowing CALDA to offer generalizable strategies for MS-UDA.

Förderung

  • NIA NIH HHS
  • NIBIB NIH HHS
  • National Science Foundation
  • National Institutes of Health

Zitieren

APA

Wilson, G., Doppa, J. R., & Cook, D. J. (2023). CALDA: Improving Multi-Source Time Series Domain Adaptation With Contrastive Adversarial Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 14208-14221. https://doi.org/10.1109/tpami.2023.3298346

Vancouver

Wilson G, Doppa JR, Cook DJ. CALDA: Improving Multi-Source Time Series Domain Adaptation With Contrastive Adversarial Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(12):14208-14221. doi:10.1109/tpami.2023.3298346

BibTeX
@article{Wilson2023,
  author = {Wilson, Garrett and Doppa, Janardhan Rao and Cook, Diane J},
  title = {CALDA: Improving Multi-Source Time Series Domain Adaptation With Contrastive Adversarial Learning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {12},
  pages = {14208--14221},
  doi = {10.1109/tpami.2023.3298346}
}
Kostenlos starten →