Decentralized Federated Learning via Mutual Knowledge Transfer
This work provides an incremental improvement for decentralized federated learning in IoT systems, aiming to mitigate client-drift and improve convergence for scenarios with heterogeneous data.
This paper addresses decentralized federated learning in IoT systems, where clients collaboratively train models without a central server or direct data sharing. The proposed Def-KT algorithm, which fuses models via mutual knowledge transfer instead of parameter averaging, significantly outperforms baseline methods like Combo and FullAvg on datasets such as MNIST and CIFAR-100, especially with non-IID data.
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.