EUVIMEDEUVIMED entdecken
Crossref

Exploring Vacant Classes in Label-Skewed Federated Learning

Kuangpu Guo, Yuhe Ding, Jian Liang, Zilei Wang, Ran He, Tieniu Tan

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (16) · 16960-16968

DOI: 10.1609/aaai.v39i16.33864 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Kuangpu Guo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training. Although these methods improve the mean accuracy across all classes, we observe that vacant classes—referring to categories absent from a client's data distribution—remain poorly recognized. Besides, there is still a gap in the accuracy of local models on minority classes compared to the global model. This paper introduces FedVLS, a novel approach to label-skewed federated learning that integrates both vacant-class distillation and logit suppression simultaneously. Specifically, vacant-class distillation leverages knowledge distillation during local training on each client to retain essential information related to vacant classes from the global model. Moreover, logit suppression directly penalizes network logits for non-label classes, effectively addressing misclassifications in minority classes that may be biased toward majority classes. Extensive experiments validate the efficacy of FedVLS, demonstrating superior performance compared to previous state-of-the-art (SOTA) methods across diverse datasets with varying degrees of label skews.

Zitieren

APA

Guo, K., Ding, Y., Liang, J., Wang, Z., He, R., & Tan, T. (2025). Exploring Vacant Classes in Label-Skewed Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(16), 16960-16968. https://doi.org/10.1609/aaai.v39i16.33864

Vancouver

Guo K, Ding Y, Liang J, Wang Z, He R, Tan T. Exploring Vacant Classes in Label-Skewed Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(16):16960-16968. doi:10.1609/aaai.v39i16.33864

BibTeX
@article{Guo2025,
  author = {Guo, Kuangpu and Ding, Yuhe and Liang, Jian and Wang, Zilei and He, Ran and Tan, Tieniu},
  title = {Exploring Vacant Classes in Label-Skewed Federated Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {16},
  pages = {16960--16968},
  doi = {10.1609/aaai.v39i16.33864}
}
Kostenlos starten →