Decentralized Federated Learning via Mutual Knowledge Transfer

Chengxi Li, Gang Li, Pramod K. Varshney

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we investigate the problem of decentralized federated learning (DFL) in Internet of things (IoT) systems, where a number of IoT clients train models collectively for a common task without sharing their private training data in the absence of a central server. Most of the existing DFL schemes are composed of two alternating steps, i.e., model updating and model averaging. However, averaging model parameters directly to fuse different models at the local clients suffers from client-drift especially when the training data are heterogeneous across different clients. This leads to slow convergence and degraded learning performance. As a possible solution, we propose the decentralized federated learning via mutual knowledge transfer (Def-KT) algorithm where local clients fuse models by transferring their learnt knowledge to each other. Our experiments on the MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets reveal that the proposed Def-KT algorithm significantly outperforms the baseline DFL methods with model averaging, i.e., Combo and FullAvg, especially when the training data are not independent and identically distributed (non-IID) across different clients.

Original languageEnglish (US)
JournalIEEE Internet of Things Journal
DOIs
StateAccepted/In press - 2021

Keywords

  • Convergence
  • Data models
  • Internet of Things
  • Internet of Things (IoT)
  • Servers
  • Task analysis
  • Training
  • Training data
  • decentralized learning
  • federated learning
  • knowledge transfer.

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Decentralized Federated Learning via Mutual Knowledge Transfer'. Together they form a unique fingerprint.

Cite this