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

arXiv: https://arxiv.org/abs/2308.04762 · HTML: https://mlsanity.com/paper/2308.04762/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 14 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 6 of 6)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications](https://mlsanity.com/paper/1907.01132/) (2019)
- [Gossip training for deep learning](https://mlsanity.com/paper/1611.09726/) (2016)
- [How to scale distributed deep learning?](https://mlsanity.com/paper/1611.04581/) (2016)

## Built on by (most cited first, 3 of 3)

- [Distributed Learning and Inference Systems: A Networking Perspective](https://mlsanity.com/paper/2501.05323/) (2025)
- [Load-Aware Training Scheduling for Model Circulation-based Decentralized Federated Learning](https://mlsanity.com/paper/2506.09769/) (2025)
- [Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks](https://mlsanity.com/paper/2603.15188/) (2026)

## Abstract (arXiv)

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.