EUVIMEDEUVIMED entdecken
Crossref

Federated Active Semi-Supervised Learning With Communication Efficiency

Chen Zhang, Yu Xie, Hang Bai, Xiongwei Hu, Bin Yu, Yuan Gao

IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2023-11 · 53 (11) · 6744-6756

DOI: 10.1109/tsmc.2023.3286485 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2023-11. Verfasst von Chen Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Key Research and Development Program of Shaanxi Program, National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) unites multiple participants to collaboratively learn a global consensus model on the centralized server by aggregating their individual models trained locally on clients. To meet the goal of obtaining an optimal model, sufficient labeled data and myriad communications are required during training. However, the major problems are the limited budget for manually annotating unlabeled instances and the restricted bandwidth of server and clients. This article presents a communication-efficient federated active semi-supervised learning (CEFedASSL) framework that unites active learning (AL) clients and a semi-supervised learning (SSL) client to train models on unlabeled data while achieving communication efficiency. In each AL client, different query strategies are, respectively, applied for the local model to obtain a more robust model and query only the optimal samples which significantly reduces the cost of annotation. Subsequently, these optimal samples are encrypted as input to fine-tune the pretrained model of the SSL client by performing self-training, thereby enhancing the model performance while preserving the privacy of data. Furthermore, we propose an efficient selective aggregation strategy to reduce the communication cost between clients and the server. Empirical experiments on four different learning tasks demonstrate that the proposed CEFedASSL distinctively outperforms the common FL algorithms in terms of both model performance and communication costs.

Förderung

  • Key Research and Development Program of Shaanxi Program
  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Fund Program for the Scientific Activities of Selected Returned Overseas Professionals in Shanxi Province

Zitieren

APA

Zhang, C., Xie, Y., Bai, H., Hu, X., Yu, B., & Gao, Y. (2023). Federated Active Semi-Supervised Learning With Communication Efficiency. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 53(11), 6744-6756. https://doi.org/10.1109/tsmc.2023.3286485

Vancouver

Zhang C, Xie Y, Bai H, Hu X, Yu B, Gao Y. Federated Active Semi-Supervised Learning With Communication Efficiency. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2023;53(11):6744-6756. doi:10.1109/tsmc.2023.3286485

BibTeX
@article{Zhang2023,
  author = {Zhang, Chen and Xie, Yu and Bai, Hang and Hu, Xiongwei and Yu, Bin and Gao, Yuan},
  title = {Federated Active Semi-Supervised Learning With Communication Efficiency},
  journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
  year = {2023},
  volume = {53},
  number = {11},
  pages = {6744--6756},
  doi = {10.1109/tsmc.2023.3286485}
}
Kostenlos starten →