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.

翻译：在去中心化联邦学习（DFL）中，频繁的节点间通信产生大量流量，且数据非独立同分布（non-IID）特性为获取高精度模型带来挑战。本文提出Tram-FL这一新型DFL方法，该方法通过在各节点间顺序传递全局模型来逐步优化，而非交换和聚合局部模型。同时，我们引入一种动态模型路由算法以选择最优路径，旨在通过最小化转发次数来提升模型精度。基于MNIST、CIFAR-10和IMDb数据集的实验表明，采用所提路由机制的Tram-FL在non-IID条件下能获得高模型精度，在降低通信成本的同时优于基线方法。