Data Distribution-Aware Online Client Selection Algorithm for Federated Learning in Heterogeneous Networks

Jaewook Lee, Haneul Ko, Sangwon Seo, Sangheon Pack

Research output: Contribution to journalArticlepeer-review


Federated learning (FL) has received significant attention as a practical alternative to traditional cloud-centric machine learning (ML). The performance (e.g., accuracy and convergence time) of FL is hampered by the selection of clients having non-independent and identically distributed (non-IID) data. In addition, a long convergence time is inevitable if clients with poor computation or communication capabilities participate in the FL procedure (i.e., the straggler problem). To minimize convergence time while guaranteeing high learning accuracy, we first formulate an optimization problem on client selection. As a practical solution, we devise a data distribution-aware online client selection (DOCS) algorithm. In DOCS, the FL server finds several clusters having near IID data and then uses a multi-armed bandit (MAB) technique to select the cluster with the lowest convergence time. The evaluation results demonstrate that DOCS can reduce the convergence time by up to <inline-formula><tex-math notation="LaTeX">$10\% \sim 41\%$</tex-math></inline-formula> and improve the learning accuracy by up to <inline-formula><tex-math notation="LaTeX">$4\% \sim 13\%$</tex-math></inline-formula> compared to the traditional client selection schemes.

Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalIEEE Transactions on Vehicular Technology
Publication statusAccepted/In press - 2022


  • client selection
  • Clustering algorithms
  • Convergence
  • Data models
  • Federated learning
  • multi-armed bandit problem
  • Optimization
  • optimization
  • Servers
  • Training
  • Wireless networks

ASJC Scopus subject areas

  • Automotive Engineering
  • Aerospace Engineering
  • Electrical and Electronic Engineering
  • Applied Mathematics


Dive into the research topics of 'Data Distribution-Aware Online Client Selection Algorithm for Federated Learning in Heterogeneous Networks'. Together they form a unique fingerprint.

Cite this