English

Twin Sorting Dynamic Programming Assisted User Association and Wireless Bandwidth Allocation for Hierarchical Federated Learning

Machine Learning 2024-08-20 v1 Networking and Internet Architecture

Abstract

In this paper, we study user association and wireless bandwidth allocation for a hierarchical federated learning system that consists of mobile users, edge servers, and a cloud server. To minimize the length of a global round in hierarchical federated learning with equal bandwidth allocation, we formulate a combinatorial optimization problem. We design the twin sorting dynamic programming (TSDP) algorithm that obtains a globally optimal solution in polynomial time when there are two edge servers. In addition, we put forward the TSDP-assisted algorithm for user association when there are three or more edge servers. Furthermore, given a user association matrix, we formulate and solve a convex optimization problem for optimal wireless bandwidth allocation. Simulation results show that the proposed approach outperforms a number of alternative schemes.

Keywords

Cite

@article{arxiv.2408.09076,
  title  = {Twin Sorting Dynamic Programming Assisted User Association and Wireless Bandwidth Allocation for Hierarchical Federated Learning},
  author = {Rung-Hung Gau and Ting-Yu Wang and Chun-Hung Liu},
  journal= {arXiv preprint arXiv:2408.09076},
  year   = {2024}
}

Comments

14 pages

R2 v1 2026-06-28T18:15:17.905Z