EUVIMEDEUVIMED entdecken
Crossref

Federated Learning and Meta Learning: Approaches, Applications, and Directions

Xiaonan Liu, Yansha Deng, Arumugam Nallanathan, Mehdi Bennis

IEEE Communications Surveys & Tutorials · 2024 · 26 (1) · 571-618

DOI: 10.1109/comst.2023.3330910 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Communications Surveys & Tutorials, 2024. Verfasst von Xiaonan Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 113-mal zitiert (Crossref) und nennt 313 Literaturangaben. Gefördert von: Engineering and Physical Sciences Research Council (EPSRC), U.K., UKRI through the U.K. Government’s Horizon Europe Funding Guarantee, European Commission-funded Collaborative Project VERGE through SNS JU Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Over the past few years, significant advancements have been made in the field of machine learning (ML) to address resource management, interference management, autonomy, and decision-making in wireless networks. Traditional ML approaches rely on centralized methods, where data is collected at a central server for training. However, this approach poses a challenge in terms of preserving the data privacy of devices. To address this issue, federated learning (FL) has emerged as an effective solution that allows edge devices to collaboratively train ML models without compromising data privacy. In FL, local datasets are not shared, and the focus is on learning a global model for a specific task involving all devices. However, FL has limitations when it comes to adapting the model to devices with different data distributions. In such cases, meta learning is considered, as it enables the adaptation of learning models to different data distributions using only a few data samples. In this tutorial, we present a comprehensive review of FL, meta learning, and federated meta learning (FedMeta). Unlike other tutorial papers, our objective is to explore how FL, meta learning, and FedMeta methodologies can be designed, optimized, and evolved, and their applications over wireless networks. We also analyze the relationships among these learning algorithms and examine their advantages and disadvantages in real-world applications.

Förderung

  • Engineering and Physical Sciences Research Council (EPSRC), U.K.
  • UKRI through the U.K. Government’s Horizon Europe Funding Guarantee
  • European Commission-funded Collaborative Project VERGE through SNS JU Program

Zitieren

APA

Liu, X., Deng, Y., Nallanathan, A., & Bennis, M. (2024). Federated Learning and Meta Learning: Approaches, Applications, and Directions. IEEE Communications Surveys & Tutorials, 26(1), 571-618. https://doi.org/10.1109/comst.2023.3330910

Vancouver

Liu X, Deng Y, Nallanathan A, Bennis M. Federated Learning and Meta Learning: Approaches, Applications, and Directions. IEEE Communications Surveys & Tutorials. 2024;26(1):571-618. doi:10.1109/comst.2023.3330910

BibTeX
@article{Liu2024,
  author = {Liu, Xiaonan and Deng, Yansha and Nallanathan, Arumugam and Bennis, Mehdi},
  title = {Federated Learning and Meta Learning: Approaches, Applications, and Directions},
  journal = {IEEE Communications Surveys & Tutorials},
  year = {2024},
  volume = {26},
  number = {1},
  pages = {571--618},
  doi = {10.1109/comst.2023.3330910}
}
Kostenlos starten →