EUVIMEDEUVIMED entdecken
Crossref

Tackling Spatial-Temporal Heterogeneous Federated Learning With Orthogonal Regularization

Chenrui Wu, Haishuai Wang, Xiang Zhang, Hongyang Chen, Jiajun Bu, Jiangchuan Liu

IEEE Transactions on Mobile Computing · 2026-06 · 25 (6) · 8667-8683

DOI: 10.1109/tmc.2026.3650937 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-06. Verfasst von Chenrui Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 99 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Province Vanguard Goose-Leading Initiative.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the proliferation of mobile sensing technology, substantial time series data have been generated and accumulated in various distributed domains, providing the basis for practical applications. Federated Learning (FL) has emerged as an essential framework for machine learning on decentralized data, especially with its potential for privacy-preserving. However, deployed with distributed and various edge devices, existing FL frameworks struggle to address the statistical heterogeneity of spatial feature distribution shifts from heterogeneous sensors. Due to the complex temporal dynamics of real-world time series data, temporal feature heterogeneity may result in suboptimal model adaptation performance. To this end, we propose a novel Federated learning approach with Orthogonal regularization for Spatial-Temporal heterogeneity (FedOST) on time series classification. It is featured in three aspects: (1) In the local training phase, we utilize an orthogonal projection to disentangle and align the shared and personalized features, as well as complementary information from different views of the time series data to formulate a robust multi-view training. (2) In the global aggregation phase, we adopt trainable global prototypes to improve feature space separation through orthogonal constraint, to serve as refined global knowledge in the local training. (3) In the testing phase, we leverage an uncertainty-aware test-time adaptation scheme to tackle the temporal feature shifts of unlabeled test data. We conduct extensive evaluations on real-world datasets, where FedOST outperforms existing state-of-the-art baselines with significant advantages.

Förderung

  • National Natural Science Foundation of China
  • Zhejiang Province Vanguard Goose-Leading Initiative

Zitieren

APA

Wu, C., Wang, H., Zhang, X., Chen, H., Bu, J., & Liu, J. (2026). Tackling Spatial-Temporal Heterogeneous Federated Learning With Orthogonal Regularization. IEEE Transactions on Mobile Computing, 25(6), 8667-8683. https://doi.org/10.1109/tmc.2026.3650937

Vancouver

Wu C, Wang H, Zhang X, Chen H, Bu J, Liu J. Tackling Spatial-Temporal Heterogeneous Federated Learning With Orthogonal Regularization. IEEE Transactions on Mobile Computing. 2026;25(6):8667-8683. doi:10.1109/tmc.2026.3650937

BibTeX
@article{Wu2026,
  author = {Wu, Chenrui and Wang, Haishuai and Zhang, Xiang and Chen, Hongyang and Bu, Jiajun and Liu, Jiangchuan},
  title = {Tackling Spatial-Temporal Heterogeneous Federated Learning With Orthogonal Regularization},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {6},
  pages = {8667--8683},
  doi = {10.1109/tmc.2026.3650937}
}
Kostenlos starten →