Personalized Federated Learning for Statistical Heterogeneity

Muhammad Firdaus; Kyung-Hyune Rhee

Personalized Federated Learning for Statistical Heterogeneity

Machine Learning 2024-02-19 v1 Networking and Internet Architecture

Authors: Muhammad Firdaus , Kyung-Hyune Rhee

Abstract

The popularity of federated learning (FL) is on the rise, along with growing concerns about data privacy in artificial intelligence applications. FL facilitates collaborative multi-party model learning while simultaneously ensuring the preservation of data confidentiality. Nevertheless, the problem of statistical heterogeneity caused by the presence of diverse client data distributions gives rise to certain challenges, such as inadequate personalization and slow convergence. In order to address the above issues, this paper offers a brief summary of the current research progress in the field of personalized federated learning (PFL). It outlines the PFL concept, examines related techniques, and highlights current endeavors. Furthermore, this paper also discusses potential further research and obstacles associated with PFL.

Keywords

federated learning federated graph learning distributed learning

Cite

@article{arxiv.2402.10254,
  title  = {Personalized Federated Learning for Statistical Heterogeneity},
  author = {Muhammad Firdaus and Kyung-Hyune Rhee},
  journal= {arXiv preprint arXiv:2402.10254},
  year   = {2024}
}

Personalized Federated Learning for Statistical Heterogeneity

Abstract

Keywords

Cite

Related papers