FEDNS: IMPROVING FEDERATED LEARNING FOR COLLABORATIVE IMAGE CLASSIFICATION ON MOBILE CLIENTS

Yaoxin Zhuo, Baoxin Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model collaboratively with the help of a centralized server. The most popular FL algorithm is Federated Averaging (FedAvg), which is based on taking weighted average of the client models, with the weights determined largely based on dataset sizes at the clients. In this paper, we propose a new approach, termed Federated Node Selection (FedNS), for the server's global model aggregation in the FL setting. FedNS filters and re-weights the clients' models at the node/kernel level, hence leading to a potentially better global model by fusing the best components of the clients. Using collaborative image classification as an example, we show with experiments from multiple datasets and networks that FedNS can consistently achieve improved performance over FedAvg.

Original languageEnglish (US)
Title of host publication2021 IEEE International Conference on Multimedia and Expo, ICME 2021
PublisherIEEE Computer Society
ISBN (Electronic)9781665438643
DOIs
StatePublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Multimedia and Expo, ICME 2021 - Shenzhen, China
Duration: Jul 5 2021Jul 9 2021

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2021 IEEE International Conference on Multimedia and Expo, ICME 2021
Country/TerritoryChina
CityShenzhen
Period7/5/217/9/21

Keywords

  • Federated learning
  • Image classification
  • Model aggregation

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'FEDNS: IMPROVING FEDERATED LEARNING FOR COLLABORATIVE IMAGE CLASSIFICATION ON MOBILE CLIENTS'. Together they form a unique fingerprint.

Cite this