EUVIMEDEUVIMED entdecken
Crossref

Tackling Data Heterogeneity in Federated Learning with Class Prototypes

Yutong Dai, Zeyuan Chen, Junnan Li, Shelby Heinecke, Lichao Sun, Ran Xu

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (6) · 7314-7322

DOI: 10.1609/aaai.v37i6.25891 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Yutong Dai und 5 weiteren Autor:innen. Die Arbeit wurde bisher 138-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data heterogeneity across clients in federated learning (FL) settings is a widely acknowledged challenge. In response, personalized federated learning (PFL) emerged as a framework to curate local models for clients' tasks. In PFL, a common strategy is to develop local and global models jointly - the global model (for generalization) informs the local models, and the local models (for personalization) are aggregated to update the global model. A key observation is that if we can improve the generalization ability of local models, then we can improve the generalization of global models, which in turn builds better personalized models. In this work, we consider class imbalance, an overlooked type of data heterogeneity, in the classification setting. We propose FedNH, a novel method that improves the local models' performance for both personalization and generalization by combining the uniformity and semantics of class prototypes. FedNH initially distributes class prototypes uniformly in the latent space and smoothly infuses the class semantics into class prototypes. We show that imposing uniformity helps to combat prototype collapse while infusing class semantics improves local models. Extensive experiments were conducted on popular classification datasets under the cross-device setting. Our results demonstrate the effectiveness and stability of our method over recent works.

Zitieren

APA

Dai, Y., Chen, Z., Li, J., Heinecke, S., Sun, L., & Xu, R. (2023). Tackling Data Heterogeneity in Federated Learning with Class Prototypes. Proceedings of the AAAI Conference on Artificial Intelligence, 37(6), 7314-7322. https://doi.org/10.1609/aaai.v37i6.25891

Vancouver

Dai Y, Chen Z, Li J, Heinecke S, Sun L, Xu R. Tackling Data Heterogeneity in Federated Learning with Class Prototypes. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(6):7314-7322. doi:10.1609/aaai.v37i6.25891

BibTeX
@article{Dai2023,
  author = {Dai, Yutong and Chen, Zeyuan and Li, Junnan and Heinecke, Shelby and Sun, Lichao and Xu, Ran},
  title = {Tackling Data Heterogeneity in Federated Learning with Class Prototypes},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {6},
  pages = {7314--7322},
  doi = {10.1609/aaai.v37i6.25891}
}
Kostenlos starten →