EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks

Yuchen Shi; Qijun Hou; Pingyi Fan; Khaled B. Letaief

cs.LGMar 3, 2026

EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks

Authors: Yuchen Shi, Qijun Hou, Pingyi Fan, Khaled B. Letaief

Organizations: Dept. of Electronic Engineering, BNRist, Tsinghua University. · Dept. of Electronic and Computer Engineering, HKUST.

Abstract

Federated Learning (FL) has emerged as a transformative distributed learning paradigm in the era of Internet of Things (IoT), reconceptualizing data processing methodologies. However, FL systems face significant communication bottlenecks due to inevitable client-server data exchanges and long-distance transmissions. This work presents EdgeFLow, an innovative FL framework that redesigns the system topology by replacing traditional cloud servers with sequential model migration between edge base stations. By conducting model aggregation and propagation exclusively at edge clusters, EdgeFLow eliminates cloud-based transmissions and substantially reduces global communication overhead. We provide rigorous convergence analysis for EdgeFLow under non-convex objectives and non-IID data distributions, extending classical FL convergence theory. Experimental results across various configurations validate the theoretical analysis, demonstrating that EdgeFLow achieves comparable accuracy improvements while significantly reducing communication costs. As a systemic architectural innovation for communication-efficient FL, EdgeFLow establishes a foundational framework for future developments in IoT and edge-network learning systems.

Figures & tables

Fig. 1: The comparison between FL, Hierarchical FL and EdgeFLow.

Panel of Figure 2 — Fig. 2: Comparative demonstration of three data configuration paradigms. NIID A features distribution skewness, whereas NIID B features both distribution and quantity skewness.

Method	FashionMNIST		CIFAR-10
Method	IID	NIID A	IID	NIID A	NIID B
FedAvg	90.60	86.89	88.66	77.04	71.04
EdgeFLowRand	90.13	87.97	89.16	80.26	73.14
EdgeFLowSeq	90.53	87.50	88.99	81.58	73.36

TABLE I: Results of Accuracy Performance (

\%

)

Panel of Figure 4 — Fig. 3: Impact of hyperparameter variations on EdgeFLow. Accuracy curves are smoothed with a sliding window for visualization.

Fig. 4: Communication load comparison across network structures.

Federated Learning

Federated learning trains shared models across data holders without requiring them to pool their raw data.

See all 921 papers

Tram-FL: Reducing Communication and Computation Costs through Sequential Model Circulation in Decentralized Federated Learning
Oct 6, 2026Kota Maejima, Takayuki Nishio, Asato Yamazaki +1Communication-Efficient Distributed Training Federated Learning
School of Engineering, Institute of Science Tokyo, Tokyo 152-8550, Japan
Benchmarking Federated Learning in Edge Computing Environments: A Systematic Review and Performance Evaluation
Feb 24, 2026Sales Aribe, Gil Nicholas CagandeFederated Learning Communication-Efficient Distributed Training
Information Technology Department, Bukidnon State University, Malaybalay City, Philippines
H-FedSN: Personalized Sparse Networks for Efficient and Accurate Hierarchical Federated Learning for IoT Applications
Dec 9, 2024Jiechao Gao, Yuangang Li, Jie Wang +3Hierarchical Federated Learning Internet of Things
University of Virginia Charlottesville, VA, USA

Oct 6, 2026J/K move · Enter open · S save

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

Kota Maejima, Takayuki Nishio, Asato Yamazaki, Yuko Hara-Azumi

School of Engineering, Institute of Science Tokyo, Tokyo 152-8550, Japan

Communication-Efficient Distributed Training Federated Learning

Open paper AskPDF arXiv

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.

Abstract

Federated Learning

Explore similar work

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

Benchmarking Federated Learning in Edge Computing Environments: A Systematic Review and Performance Evaluation

H-FedSN: Personalized Sparse Networks for Efficient and Accurate Hierarchical Federated Learning for IoT Applications