EUVIMEDEUVIMED entdecken
Crossref

FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels

Jichang Li, Guanbin Li, Hui Cheng, Zicheng Liao, Yizhou Yu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 3118-3126

DOI: 10.1609/aaai.v38i4.28095 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jichang Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning with Noisy Labels (F-LNL) aims at seeking an optimal server model via collaborative distributed learning by aggregating multiple client models trained with local noisy or clean samples. On the basis of a federated learning framework, recent advances primarily adopt label noise filtering to separate clean samples from noisy ones on each client, thereby mitigating the negative impact of label noise. However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability. In this paper, we present FedDiv to tackle the challenges of F-LNL. Specifically, we propose a global noise filter called Federated Noise Filter for effectively identifying samples with noisy labels on every client, thereby raising stability during local training sessions. Without sacrificing data privacy, this is achieved by modeling the global distribution of label noise across all clients. Then, in an effort to make the global model achieve higher performance, we introduce a Predictive Consistency based Sampler to identify more credible local data for local model training, thus preventing noise memorization and further boosting the training stability. Extensive experiments on CIFAR-10, CIFAR-100, and Clothing1M demonstrate that FedDiv achieves superior performance over state-of-the-art F-LNL methods under different label noise settings for both IID and non-IID data partitions. Source code is publicly available at https://github.com/lijichang/FLNL-FedDiv.

Zitieren

APA

Li, J., Li, G., Cheng, H., Liao, Z., & Yu, Y. (2024). FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3118-3126. https://doi.org/10.1609/aaai.v38i4.28095

Vancouver

Li J, Li G, Cheng H, Liao Z, Yu Y. FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):3118-3126. doi:10.1609/aaai.v38i4.28095

BibTeX
@article{Li2024,
  author = {Li, Jichang and Li, Guanbin and Cheng, Hui and Liao, Zicheng and Yu, Yizhou},
  title = {FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {4},
  pages = {3118--3126},
  doi = {10.1609/aaai.v38i4.28095}
}
Kostenlos starten →