EUVIMEDEUVIMED entdecken
Crossref

Federated Learning with Extremely Noisy Clients via Negative Distillation

Yang Lu, Lin Chen, Yonggang Zhang, Yiliang Zhang, Bo Han, Yiu-ming Cheung, Hanzi Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (13) · 14184-14192

DOI: 10.1609/aaai.v38i13.29329 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yang Lu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) has shown remarkable success in cooperatively training deep models, while typically struggling with noisy labels. Advanced works propose to tackle label noise by a re-weighting strategy with a strong assumption, i.e., mild label noise. However, it may be violated in many real-world FL scenarios because of highly contaminated clients, resulting in extreme noise ratios, e.g., >90%. To tackle extremely noisy clients, we study the robustness of the re-weighting strategy, showing a pessimistic conclusion: minimizing the weight of clients trained over noisy data outperforms re-weighting strategies. To leverage models trained on noisy clients, we propose a novel approach, called negative distillation (FedNed). FedNed first identifies noisy clients and employs rather than discards the noisy clients in a knowledge distillation manner. In particular, clients identified as noisy ones are required to train models using noisy labels and pseudo-labels obtained by global models. The model trained on noisy labels serves as a ‘bad teacher’ in knowledge distillation, aiming to decrease the risk of providing incorrect information. Meanwhile, the model trained on pseudo-labels is involved in model aggregation if not identified as a noisy client. Consequently, through pseudo-labeling, FedNed gradually increases the trustworthiness of models trained on noisy clients, while leveraging all clients for model aggregation through negative distillation. To verify the efficacy of FedNed, we conduct extensive experiments under various settings, demonstrating that FedNed can consistently outperform baselines and achieve state-of-the-art performance.

Zitieren

APA

Lu, Y., Chen, L., Zhang, Y., Zhang, Y., Han, B., Cheung, Y., & Wang, H. (2024). Federated Learning with Extremely Noisy Clients via Negative Distillation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(13), 14184-14192. https://doi.org/10.1609/aaai.v38i13.29329

Vancouver

Lu Y, Chen L, Zhang Y, Zhang Y, Han B, Cheung Y, et al. Federated Learning with Extremely Noisy Clients via Negative Distillation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(13):14184-14192. doi:10.1609/aaai.v38i13.29329

BibTeX
@article{Lu2024,
  author = {Lu, Yang and Chen, Lin and Zhang, Yonggang and Zhang, Yiliang and Han, Bo and Cheung, Yiu-ming and Wang, Hanzi},
  title = {Federated Learning with Extremely Noisy Clients via Negative Distillation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {13},
  pages = {14184--14192},
  doi = {10.1609/aaai.v38i13.29329}
}
Kostenlos starten →