Decentralized Federated Learning via Mutual Knowledge Transfer

TL;DR

This paper introduces Def-KT, a decentralized federated learning algorithm that enhances model training in IoT systems by mutual knowledge transfer, addressing client-drift issues caused by data heterogeneity.

Contribution

The paper proposes a novel Def-KT algorithm for decentralized federated learning that improves convergence and performance over traditional averaging methods in non-IID data scenarios.

Findings

Def-KT outperforms baseline methods on multiple datasets.

Mutual knowledge transfer reduces client-drift in heterogeneous data.

Significant improvements in convergence speed and accuracy.

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 earning 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.