Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2022

Major/Subject

Mcode

Degree programme

Language

en

Pages

8
27-34

Series

IEEE INTELLIGENT SYSTEMS, Volume 37, issue 2

Abstract

Federated learning (FL) is a novel machine learning setting that enables on-device intelligence via decentralized training and federated optimization. Deep neural networks' rapid development facilitates the learning techniques for modeling complex problems and emerges into federated deep learning under the federated setting. However, the tremendous amount of model parameters burdens the communication network with a high load of transportation. This article introduces two approaches for improving communication efficiency by dynamic sampling and top-k selective masking. The former controls the fraction of selected client models dynamically, while the latter selects parameters with top-k largest values of difference for federated updating. Experiments on convolutional image classification and recurrent language modeling are conducted on three public datasets to show our proposed methods' effectiveness.

Description

Publisher Copyright: Author

Keywords

Collaborative work, Computational modeling, Costs, Heuristic algorithms, Servers, Training, Transportation

Other note

Citation

Ji, S, Jiang, W, Walid, A & Li, X 2022, ' Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning ', IEEE Intelligent Systems, vol. 37, no. 2, pp. 27-34 . https://doi.org/10.1109/MIS.2021.3114610