Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Delay and Overhead Efficient Transmission Scheduling for Federated Learning in UAV Swarms

Duc N. M. Hoang, Vu Tuan Truong, Hung Duy Le, Long Bao Le

TL;DR

This paper studies the wireless scheduling design to coordinate the transmissions of (local) model parameters of federated learning (FL) for a swarm of unmanned aerial vehicles (UAVs) and theoretically shows that the proposed scheme achieves minimal delay and communication overhead.

Abstract

This paper studies the wireless scheduling design to coordinate the transmissions of (local) model parameters of federated learning (FL) for a swarm of unmanned aerial vehicles (UAVs). The overall goal of the proposed design is to realize the FL training and aggregation processes with a central aggregator exploiting the sensory data collected by the UAVs but it considers the multi-hop wireless network formed by the UAVs. Such transmissions of model parameters over the UAV-based wireless network potentially cause large transmission delays and overhead. Our proposed framework smartly aggregates local model parameters trained by the UAVs while efficiently transmitting the underlying parameters to the central aggregator in each FL global round. We theoretically show that the proposed scheme achieves minimal delay and communication overhead. Extensive numerical experiments demonstrate the superiority of the proposed scheme compared to other baselines.

Delay and Overhead Efficient Transmission Scheduling for Federated Learning in UAV Swarms

TL;DR

This paper studies the wireless scheduling design to coordinate the transmissions of (local) model parameters of federated learning (FL) for a swarm of unmanned aerial vehicles (UAVs) and theoretically shows that the proposed scheme achieves minimal delay and communication overhead.

Abstract

This paper studies the wireless scheduling design to coordinate the transmissions of (local) model parameters of federated learning (FL) for a swarm of unmanned aerial vehicles (UAVs). The overall goal of the proposed design is to realize the FL training and aggregation processes with a central aggregator exploiting the sensory data collected by the UAVs but it considers the multi-hop wireless network formed by the UAVs. Such transmissions of model parameters over the UAV-based wireless network potentially cause large transmission delays and overhead. Our proposed framework smartly aggregates local model parameters trained by the UAVs while efficiently transmitting the underlying parameters to the central aggregator in each FL global round. We theoretically show that the proposed scheme achieves minimal delay and communication overhead. Extensive numerical experiments demonstrate the superiority of the proposed scheme compared to other baselines.
Paper Structure (17 sections, 2 theorems, 2 equations, 7 figures, 1 algorithm)

This paper contains 17 sections, 2 theorems, 2 equations, 7 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Federated Learning in UAV Swarms
  4. Collaborative Sensing and Training Procedure
  5. Delay and Overhead Analyses
  6. Scheduling Problem
  7. Proposed Scheduling Scheme
  8. Root Node Selection and Associated Delay
  9. Communication Overhead Analysis
  10. Proposed Scheduling Scheme
  11. Complexity Analysis
  12. Numerical Results
  13. Experiment Settings
  14. Convergence Results
  15. Delay and Overhead Results
  16. ...and 2 more sections

Key Result

Proposition 1

At the end of global round $r$, the proposed transmission scheduling scheme in algo:sched achieves:

Figures (7)

  • Figure 1: Example of UAV swarm deployment.
  • Figure 2: Illustrations of transmission schemes: (a) Independent transmissions, (b) Combined aggregation and transmissions.
  • Figure 3: Example of proposed transmission scheduler.
  • Figure 4: Loss and accuracy with MNIST dataset.
  • Figure 5: Loss and accuracy with CIFAR-10 dataset.
  • ...and 2 more figures

Theorems & Definitions (4)

  • Proposition 1
  • proof
  • Lemma 1
  • proof