In decentralized federated learning (DFL), substantial traffic from frequent inter-node communication and non-independent and identically distributed (non-IID) data challenges high-accuracy model acquisition. We propose Tram-FL, a novel DFL method, which progressively refines a global model by transferring it sequentially amongst nodes, rather than by exchanging and aggregating local models. We also introduce a dynamic model routing algorithm for optimal route selection, aimed at enhancing model precision with minimal forwarding. Our experiments using MNIST, CIFAR-10, and IMDb datasets demonstrate that Tram-FL with the proposed routing delivers high model accuracy under non-IID conditions, outperforming baselines while reducing communication costs.
@article{arxiv.2308.04762,
title = {Tram-FL: Routing-based Model Training for Decentralized Federated Learning},
author = {Kota Maejima and Takayuki Nishio and Asato Yamazaki and Yuko Hara-Azumi},
journal= {arXiv preprint arXiv:2308.04762},
year = {2024}
}
Comments
This work has been submitted to the IEEE for possible publication