Tram-FL: Routing-based Model Training for Decentralized Federated Learning

Autor:	Maejima, Kota, Nishio, Takayuki, Yamazaki, Asato, Hara-Azumi, Yuko
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Distributed Parallel and Cluster Computing Computer Science - Networking and Internet Architecture 68T20 (Primary) 68M14 (Secondary) I.2.7 I.2.8 I.2.10 I.2.11
Druh dokumentu:	Working Paper
Popis:	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. Comment: This work has been submitted to the IEEE for possible publication
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2308.04762 Zobrazit plný text záznamu View this record from Arxiv