Communication-Loss Trade-Off in Federated Learning: A Distributed Client Selection Algorithm

Minoo Hosseinzadeh, Nathaniel Hudson, Sam Heshmati, Hana Khamfroush

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations


Mass data generation occurring in the Internet-of-Things (IoT) requires processing to extract meaningful information. Deep learning is commonly used to perform such processing. However, due to the sensitive nature of these data, it is important to consider data privacy. As such, federated learning (FL) has been proposed to address this issue. FL pushes training to the client devices and tasks a central server with aggregating collected model weights to update a global model. However, the transmission of these model weights can be costly, gradually. The trade-off between communicating model weights for aggregation and the loss provided by the global model remains an open problem. In this work, we cast this trade-off problem of client selection in FL as an optimization problem. We then design a Distributed Client Selection (DCS) algorithm that allows client devices to decide to participate in aggregation in hopes of minimizing overall communication cost - while maintaining low loss. We evaluate the performance of our proposed client selection algorithm against standard FL and a state-of-the-art client selection algorithm, called Power-of-Choice (PoC), using CIFAR-10, FMNIST, and MNIST datasets. Our experimental results confirm that our DCS algorithm is able to closely match the loss provided by the standard FL and PoC, while on average reducing the overall communication cost by nearly 32.67% and 44.71% in comparison to standard FL and PoC, respectively.

Original languageEnglish
JournalProceedings - IEEE Consumer Communications and Networking Conference, CCNC
StatePublished - 2022
Event19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022 - Virtual, Online, United States
Duration: Jan 8 2022Jan 11 2022

Bibliographical note

Publisher Copyright:
© 2022 IEEE.


  • Client Selection
  • Distributed Learning
  • Federated Learning
  • Internet-of-Things
  • Machine Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering


Dive into the research topics of 'Communication-Loss Trade-Off in Federated Learning: A Distributed Client Selection Algorithm'. Together they form a unique fingerprint.

Cite this