articleIEEE Transactions on Neural Networks and Learning SystemsMar 28, 2022GREEN OA

Towards Personalized Federated Learning

AZAlysa Ziying TanHYHan YuLCLizhen CuiQYQiang Yang

Nanyang Technological University · Shandong University · +1 more institution

PubMed
Indexed inarxivcrossrefpubmed

Abstract

In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL…

Citation impact

995
total citations
FWCI
126.65
Percentile
100%
References
110
Citations per year

Authors

4
  • AZ
    Alysa Ziying TanCorresponding

    Nanyang Technological University

  • HY
    Han Yu

    Nanyang Technological University

  • LC
    Lizhen Cui

    Shandong University

  • QY
    Qiang Yang

    Hong Kong University of Science and Technology

Topics & keywords

Topics
Keywords
  • Personalization
  • Trustworthiness
  • Key (lock)
  • Popularity
  • Federated learning
No related works found for this paper.

Funding