Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective

By Jie Xu, Heqiang Wang. IEEE Transactions on Wireless Communications, 2020

457 citations recorded by the source corpus.

This paper studies federated learning (FL) in a classic wireless network, where learning clients share a common wireless link to a coordinating server to perform federated model training using their local data. In such wireless federated learning networks (WFLNs), optimizing the learning performance depends crucially on how clients are selected and how bandwidth is allocated among the selected clients in every learning round, as both radio and client energy resources are limited. While existing works have made some attempts to allocate the limited wireless resources to optimize FL, they focus on the problem in individual learning rounds, overlooking an inherent yet critical feature of federated learning. This paper brings a new long-term perspective to resource allocation in WFLNs, realizing that learning rounds are not only temporally interdependent but also have varying significance towards the final learning outcome. To this end, we first design data-driven experiments to show that different temporal client selection patterns lead to considerably different learning performance. With the obtained insights, we formulate a stochastic optimization problem for joint client selection and bandwidth allocation under long-term client energy constraints, and develop a new algorithm that utilizes only currently available wireless channel information but can achieve long-term performance guarantee. Experiments show that our algorithm results in the desired temporal client selection pattern, is adaptive to changing network environments and far outperforms benchmarks that ignore the long-term effect of FL.

Subfields: Artificial Intelligence, Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/e22145957a19a7999116013e26244c611b69223b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. H. Vincent Poor
  2. Mingzhe Chen
  3. Medhi Bennis
  4. Walid Saad
  5. Deniz Gündüz
  6. Kaibin Huang
  7. Azzam Mourad
  8. Aneta Vulgarakis Feljan

In Computer Networks and Communications

  1. Medhi Bennis
  2. Walid Saad
  3. Mingzhe Chen
  4. H. Vincent Poor
  5. Merouane Debbah
  6. Kaibin Huang
  7. Mohsen Guizani
  8. Deniz Gündüz

In Electrical and Electronic Engineering

  1. Medhi Bennis
  2. H. Vincent Poor
  3. Walid Saad
  4. Mingzhe Chen
  5. Merouane Debbah
  6. Deniz Gündüz
  7. Kaibin Huang
  8. Rui Zhang

Citations in the corpus