EUVIMEDEUVIMED entdecken
Crossref

UFDA: Universal Federated Domain Adaptation with Practical Assumptions

Xinhui Liu, Zhenghao Chen, Luping Zhou, Dong Xu, Wei Xi, Gairui Bai, Yihan Zhao, Jizhong Zhao

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (12) · 14026-14034

DOI: 10.1609/aaai.v38i12.29311 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xinhui Liu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional Federated Domain Adaptation (FDA) approaches usually demand an abundance of assumptions, which makes them significantly less feasible for real-world situations and introduces security hazards. This paper relaxes the assumptions from previous FDAs and studies a more practical scenario named Universal Federated Domain Adaptation (UFDA). It only requires the black-box model and the label set information of each source domain, while the label sets of different source domains could be inconsistent, and the target-domain label set is totally blind. Towards a more effective solution for our newly proposed UFDA scenario, we propose a corresponding methodology called Hot-Learning with Contrastive Label Disambiguation (HCLD). It particularly tackles UFDA's domain shifts and category gaps problems by using one-hot outputs from the black-box models of various source domains. Moreover, to better distinguish the shared and unknown classes, we further present a cluster-level strategy named Mutual-Voting Decision (MVD) to extract robust consensus knowledge across peer classes from both source and target domains. Extensive experiments on three benchmark datasets demonstrate that our method achieves comparable performance for our UFDA scenario with much fewer assumptions, compared to previous methodologies with comprehensive additional assumptions.

Zitieren

APA

Liu, X., Chen, Z., Zhou, L., Xu, D., Xi, W., Bai, G., Zhao, Y., & Zhao, J. (2024). UFDA: Universal Federated Domain Adaptation with Practical Assumptions. Proceedings of the AAAI Conference on Artificial Intelligence, 38(12), 14026-14034. https://doi.org/10.1609/aaai.v38i12.29311

Vancouver

Liu X, Chen Z, Zhou L, Xu D, Xi W, Bai G, et al. UFDA: Universal Federated Domain Adaptation with Practical Assumptions. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(12):14026-14034. doi:10.1609/aaai.v38i12.29311

BibTeX
@article{Liu2024,
  author = {Liu, Xinhui and Chen, Zhenghao and Zhou, Luping and Xu, Dong and Xi, Wei and Bai, Gairui and Zhao, Yihan and Zhao, Jizhong},
  title = {UFDA: Universal Federated Domain Adaptation with Practical Assumptions},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {12},
  pages = {14026--14034},
  doi = {10.1609/aaai.v38i12.29311}
}
Kostenlos starten →