Federated Unsupervised Domain Generalization Using Global and Local Alignment of Gradients
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (19) · 19948-19958
DOI: 10.1609/aaai.v39i19.34197 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Farhad Pourpanah und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).
Abstract (Originalsprache)
We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alignment of gradients in unsupervised federated learning and show that aligning the gradients at both client and server levels can facilitate the generalization of the model to new (target) domains. Building on this insight, we propose a novel method named FedGaLA, which performs gradient alignment at the client level to encourage clients to learn domain-invariant features, as well as global gradient alignment at the server to obtain a more generalized aggregated model. To empirically evaluate our method, we perform various experiments on four commonly used multi-domain datasets, PACS, OfficeHome, DomainNet, and TerraInc. The results demonstrate the effectiveness of our method which outperforms comparable baselines. Ablation and sensitivity studies demonstrate the impact of different components and parameters in our approach.
Zitieren
APA
Pourpanah, F., Molahasani, M., Soltany, M., Greenspan, M., & Etemad, A. (2025). Federated Unsupervised Domain Generalization Using Global and Local Alignment of Gradients. Proceedings of the AAAI Conference on Artificial Intelligence, 39(19), 19948-19958. https://doi.org/10.1609/aaai.v39i19.34197
Vancouver
Pourpanah F, Molahasani M, Soltany M, Greenspan M, Etemad A. Federated Unsupervised Domain Generalization Using Global and Local Alignment of Gradients. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(19):19948-19958. doi:10.1609/aaai.v39i19.34197
BibTeX
@article{Pourpanah2025,
author = {Pourpanah, Farhad and Molahasani, Mahdiyar and Soltany, Milad and Greenspan, Michael and Etemad, Ali},
title = {Federated Unsupervised Domain Generalization Using Global and Local Alignment of Gradients},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {19},
pages = {19948--19958},
doi = {10.1609/aaai.v39i19.34197}
}
EUVIMED