MLMG: Multi-Local and Multi-Global Model Aggregation for Federated Learning

Yang Qin, Masaaki Kondo

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

Abstract

Federated learning has attracted much interest and attention as a solution to collaboratively learn a prediction model without sharing the training data of users. Existing federated learning approaches usually develop a single independent local model for each client to train their privacy-sensitive data, afterward adopt a single centralized global model to exchange the trained parameters of clients that participate in federated training. However, given the diverse characteristics of local data and the heterogeneity across participating clients, the conventional federated learning paradigm may not achieve uniformly good performance over all users. In this work, we propose a novel federated learning mechanism which suggests using a Multi-Local and Multi-Global (MLMG) model aggregation to train the non-IID user data with clustering methods. Then a Matching algorithm is introduced to derive the appropriate exchanges between local models and global models. The new federated learning mechanism helps separate the data and user with different characteristics, thus makes it easier to capture the heterogeneity of data distributions across the users. We choose the latest on-device neural network for anomaly detection to evaluate the proposal, and experimental results based on several benchmark datasets demonstrate better detection accuracy (up to 2.83% accuracy improvement) of the novel paradigm compared with a conventional federated learning approach.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages565-571
Number of pages7
ISBN (Electronic)9781665404242
DOIs
Publication statusPublished - 2021 Mar 22
Externally publishedYes
Event2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2021 - Kassel, Germany
Duration: 2021 Mar 222021 Mar 26

Publication series

Name2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2021

Conference

Conference2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2021
Country/TerritoryGermany
CityKassel
Period21/3/2221/3/26

Keywords

  • aggregation mechanism
  • anomaly detection
  • federated learning
  • multi-local and multi-global
  • on-device neural network

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Fingerprint

Dive into the research topics of 'MLMG: Multi-Local and Multi-Global Model Aggregation for Federated Learning'. Together they form a unique fingerprint.

Cite this