Tram-FL: Routing-based Model Training for Decentralized Federated Learning
This addresses communication efficiency and accuracy issues in decentralized federated learning for distributed systems, representing an incremental improvement over existing methods.
The paper tackles the challenges of high communication traffic and non-IID data in decentralized federated learning by proposing Tram-FL, a method that sequentially transfers a global model among nodes instead of aggregating local models, achieving high accuracy and reduced communication costs in experiments on MNIST, CIFAR-10, and IMDb datasets.
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.