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

In decentralized federated learning (DFL), the dual challenges of extensive inter-node communication and nonindependent, identically distributed (non-IID) data impede the attainment of high-accuracy models while maintaining minimal communication traffic. We propose Tram-FL, which progressively refines a global model by transferring it sequentially amongst nodes. We also introduce a dynamic model routing algorithm for optimal route selection, aimed at enhancing model precision with minimal forwarding. Our experiments demonstrate that TramFL with the proposed routing delivers high model accuracy, outperforming baselines while reducing communication costs.