Automated Federated Learning in Mobile-Edge Networks - Fast Adaptation and Convergence

Chaoqun You, Kun Guo, Gang Feng, Peng Yang, Tony Q.S. Quek

研究成果: Article同行評審

1 引文 斯高帕斯(Scopus)

摘要

Federated learning (FL) can be used in mobile-edge networks to train machine learning models in a distributed manner. Recently, FL has been interpreted within a model-agnostic meta-learning (MAML) framework, which brings FL significant advantages in fast adaptation and convergence over heterogeneous data sets. However, existing research simply combines MAML and FL without explicitly addressing how much benefit MAML brings to FL and how to maximize such benefit over mobile-edge networks. In this article, we quantify the benefit from two aspects: 1) optimizing FL hyperparameters (i.e., sampled data size and the number of communication rounds) and 2) resource allocation (i.e., transmit power) in mobile-edge networks. Specifically, we formulate the MAML-based FL design as an overall learning time minimization problem, under the constraints of model accuracy and energy consumption. Facilitated by the convergence analysis of MAML-based FL, we decompose the formulated problem and then solve it using analytical solutions and the coordinate descent method. With the obtained FL hyperparameters and resource allocation, we design an MAML-based FL algorithm, called automated FL (AutoFL), that is able to conduct fast adaptation and convergence. Extensive experimental results verify that AutoFL outperforms other benchmark algorithms regarding the learning time and convergence performance.

原文English
頁(從 - 到)13571-13586
頁數16
期刊IEEE Internet of Things Journal
10
發行號15
DOIs
出版狀態Published - 2023 8月 1

All Science Journal Classification (ASJC) codes

  • 訊號處理
  • 資訊系統
  • 硬體和架構
  • 電腦科學應用
  • 電腦網路與通信

指紋

深入研究「Automated Federated Learning in Mobile-Edge Networks - Fast Adaptation and Convergence」主題。共同形成了獨特的指紋。

引用此