EUVIMEDEUVIMED entdecken
Crossref

Federated Learning with Sample-level Client Drift Mitigation

Haoran Xu, Jiaze Li, Wanyi Wu, Hao Ren

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (20) · 21752-21760

DOI: 10.1609/aaai.v39i20.35480 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Haoran Xu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning (FL) suffers from severe performance degradation due to the data heterogeneity among clients. Existing works reveal that the fundamental reason is that data heterogeneity can cause client drift where the local model update deviates from the global one, and thus they usually tackle this problem from the perspective of calibrating the obtained local update. Despite effectiveness, existing methods substantially lack a deep understanding of how heterogeneous data samples contribute to the formation of client drift. In this paper, we bridge this gap by identifying that the drift can be viewed as a cumulative manifestation of biases present in all local samples and the bias between samples is different. Besides, the bias dynamically changes as the FL training progresses. Motivated by this, we propose FedBSS that first mitigates the heterogeneity issue in a sample-level manner, orthogonal to existing methods. Specifically, the core idea of our method is to adopt a bias-aware sample selection scheme that dynamically selects the samples from small biases to large epoch by epoch to train progressively the local model in each round. In order to ensure the stability of training, we set the diversified knowledge acquisition stage as the warm-up stage to avoid the local optimality caused by knowledge deviation in the early stage of the model. Evaluation results show that FedBSS outperforms state-of-the-art baselines. In addition, we also achieved effective results on feature distribution skew and noise label dataset setting, which proves that FedBSS can not only reduce heterogeneity, but also has scalability and robustness.

Zitieren

APA

Xu, H., Li, J., Wu, W., & Ren, H. (2025). Federated Learning with Sample-level Client Drift Mitigation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(20), 21752-21760. https://doi.org/10.1609/aaai.v39i20.35480

Vancouver

Xu H, Li J, Wu W, Ren H. Federated Learning with Sample-level Client Drift Mitigation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(20):21752-21760. doi:10.1609/aaai.v39i20.35480

BibTeX
@article{Xu2025,
  author = {Xu, Haoran and Li, Jiaze and Wu, Wanyi and Ren, Hao},
  title = {Federated Learning with Sample-level Client Drift Mitigation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {20},
  pages = {21752--21760},
  doi = {10.1609/aaai.v39i20.35480}
}
Kostenlos starten →