Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UAV-Assisted Multi-Task Federated Learning with Task Knowledge Sharing

Yubo Yang, Tao Yang, Xiaofeng Wu, Bo Hu

TL;DR

This paper proposes a UAV-assisted multi-task federated learning scheme, in which data collected by multiple UAVs can be used to train multiple related tasks concurrently, and introduces a task attention mechanism to balance task performance and encourage knowledge sharing.

Abstract

The rapid development of Unmanned aerial vehicles (UAVs) technology has spawned a wide variety of applications, such as emergency communications, regional surveillance, and disaster relief. Due to their limited battery capacity and processing power, multiple UAVs are often required for complex tasks. In such cases, a control center is crucial for coordinating their activities, which fits well with the federated learning (FL) framework. However, conventional FL approaches often focus on a single task, ignoring the potential of training multiple related tasks simultaneously. In this paper, we propose a UAV-assisted multi-task federated learning scheme, in which data collected by multiple UAVs can be used to train multiple related tasks concurrently. The scheme facilitates the training process by sharing feature extractors across related tasks and introduces a task attention mechanism to balance task performance and encourage knowledge sharing. To provide an analytical description of training performance, the convergence analysis of the proposed scheme is performed. Additionally, the optimal bandwidth allocation for UAVs under limited bandwidth conditions is derived to minimize communication time. Meanwhile, a UAV-EV association strategy based on coalition formation game is proposed. Simulation results validate the effectiveness of the proposed scheme in enhancing multi-task performance and training speed.

UAV-Assisted Multi-Task Federated Learning with Task Knowledge Sharing

TL;DR

This paper proposes a UAV-assisted multi-task federated learning scheme, in which data collected by multiple UAVs can be used to train multiple related tasks concurrently, and introduces a task attention mechanism to balance task performance and encourage knowledge sharing.

Abstract

The rapid development of Unmanned aerial vehicles (UAVs) technology has spawned a wide variety of applications, such as emergency communications, regional surveillance, and disaster relief. Due to their limited battery capacity and processing power, multiple UAVs are often required for complex tasks. In such cases, a control center is crucial for coordinating their activities, which fits well with the federated learning (FL) framework. However, conventional FL approaches often focus on a single task, ignoring the potential of training multiple related tasks simultaneously. In this paper, we propose a UAV-assisted multi-task federated learning scheme, in which data collected by multiple UAVs can be used to train multiple related tasks concurrently. The scheme facilitates the training process by sharing feature extractors across related tasks and introduces a task attention mechanism to balance task performance and encourage knowledge sharing. To provide an analytical description of training performance, the convergence analysis of the proposed scheme is performed. Additionally, the optimal bandwidth allocation for UAVs under limited bandwidth conditions is derived to minimize communication time. Meanwhile, a UAV-EV association strategy based on coalition formation game is proposed. Simulation results validate the effectiveness of the proposed scheme in enhancing multi-task performance and training speed.
Paper Structure (19 sections, 2 theorems, 19 equations, 5 figures, 1 table)

This paper contains 19 sections, 2 theorems, 19 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. System Model
  3. Federated Learning System
  4. Computation Model
  5. Communication Model
  6. PROBLEM FORMULATION AND CONVERGENCE ANALYSIS
  7. Problem Formulation
  8. Convergence Analysis
  9. Proposed Algorithm
  10. Task Attention Mechanism
  11. Task Performance Balance
  12. Task Shapley Value
  13. Optimal Bandwidth Allocation
  14. Optimal UAV-EV Association
  15. Numerical Results
  16. ...and 4 more sections

Key Result

Theorem 1

Given the UAV-EV association $\beta_t$ in round $t$, when the learning rate $\eta < \frac{2}{K^2(L_u + 2L_{su})}$, the difference in the loss function for task $m$ between two consecutive rounds is bounded by: where $\Omega_1=(4\eta K+16K^2L_{su})\epsilon_s^2+4\eta K\epsilon_u^2$, $\Omega_2=8K^2\sigma_sL_{su}\epsilon _s+4K\epsilon _s^2$, $\Omega_3=K\sigma _s(\epsilon _s+2K\sigma _sL_{su})+\frac{\

Figures (5)

  • Figure 1: UAV assisted multi-task federated learning system.
  • Figure 2: Average Accuracy
  • Figure 3: Variance
  • Figure 5: Accuracy Improvement
  • Figure 6: Total Time

Theorems & Definitions (8)

  • Theorem 1
  • Theorem 2
  • Definition 1
  • Definition 2
  • Definition 3
  • Definition 4
  • Definition 5
  • Definition 6