Tram-FL: Reducing Communication and Computation Costs through Sequential Model Circulation in Decentralized Federated Learning

2026-10-06

AI Summary

This study addresses the high computational and communication overhead caused by non-independent and identically distributed (non-IID) data in decentralized federated learning by proposing Tram-FL. Unlike conventional approaches, this mechanism innovatively focuses on models rather than clients, enabling a single model to be trained sequentially across nodes in a cyclic manner. To optimize iteration allocation, Tram-FL designs a scheduling strategy based on cyclic routing paths, which is further integrated with quantized momentum techniques and an intelligent node selection algorithm to effectively suppress transmission loads. Experimental results demonstrate that Tram-FL significantly reduces both communication and computation costs under non-IID settings while achieving high-accuracy convergence. Consequently, it provides an efficient solution for resource-constrained decentralized learning scenarios.

Abstract

Conventional decentralized federated learning (DFL) often focuses on clients, with each client maintaining a model copy, performing updates individually, and undertaking model exchange and integration. While fully leveraging computational resources can shorten training times, it can also lead to significant computational and communication waste. This is especially pronounced with non-independent and identically distributed (non-IID) data, where achieving high model accuracy demands extra resources. This research shifts focus to the model itself, aiming to realize DFL with minimal computation and communication costs. To this end, we propose Tram-FL (Traveling Model Training Mechanism for Decentralized Federated Learning), a mechanism designed to efficiently address these challenges. It sequentially trains a single model by circulating it among nodes. We address the training scheduling problem in model circulation-based training, specifically determining which nodes should update the model and the number of updates to perform. This is approached by considering the model's circulation route and update iteration allocation, for which we propose simple yet effective methods. Additionally, with quantized momentum, Tram-FL achieves high accuracy with fewer model circulations while controlling communication load per transmission. Experimental results show that the proposed algorithm, even with non-IID data, converges to a global model with reduced communication and computation.

Problem

• Decentralized Federated Learning
• Communication Cost
• Computation Cost
• Non-IID Data

Innovation

• Decentralized Federated Learning
• Traveling Model
• Training Scheduling
• Quantized Momentum
• Non-IID Data