Centralized vs Decentralized Federated Learning: A trade-off performance analysis

Chaimaa Medjadji; Guilain Leduc; Sylvain Kubler; Yves Le Traon

cs.LGMay 15, 2026

Centralized vs Decentralized Federated Learning: A trade-off performance analysis

Authors: Chaimaa Medjadji, Guilain Leduc, Sylvain Kubler, Yves Le Traon

Organizations: University of Luxembourg

Abstract

Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed edge devices while preserving data privacy especially with the huge increase amount of data due to the adoption of technologies which contributes to the growing number of IoT devices. Storing this amount of data centrally is challenging due to issues like limited communication, privacy, and regulations. FL can be Centralized (CFL), Decentralized (DFL), and Semi-decentralized (SDFL). Choosing the right FL architecture depends on the application's needs. However, very few research studies have experimentally compared these three types of architectures to not only understand the respective strengths and limitations, but also trade-offs between different performance indicators. This paper overcome this lack of analysis, conducting experimental analyses using the Fedstellar simulator, MNIST dataset, and MLP classifier.

Explore similar work

FLAM: Evaluating Model Performance with Aggregatable Measures in Federated Learning
May 8, 2026Fabian Stricker, Jose A. Peregrina, David Bermbach +1Federated Learning Model Evaluation
Efficiently Distributed Federated Learning
Sep 17, 2026Gianluca Mittone, Robert Birke, Marco AldinucciFederated Learning Heterogeneous Edge Devices
Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning
Aug 3, 2026Yuan-Heng Tsai, Li-Hsing Yen, Yan-Wei ChenFederated Learning

May 8, 2026 · cs.LGJ/K move · Enter open · S save

FLAM: Evaluating Model Performance with Aggregatable Measures in Federated Learning

Fabian Stricker, Jose A. Peregrina, David Bermbach, Christian Zirpins

Institute of Data-Centric Software Systems (IDSS), Hochschule Karlsruhe, Karlsruhe, Germany · Scalable Software Systems Research Group, TU Berlin, Berlin, Germany

Performance evaluation is essential for assessing the quality of machine learning (ML) models and guiding deployment decisions. In federated learning (FL), assessing the performance is challenging because data are distributed across participants. Consequently, the coordinator must rely on locally computed evaluation metrics and aggregate them to assess the global model. A key challenge is that common aggregation strategies, such as weighted averaging based on the local samples per participant, do not always produce the same results as centralized evaluation. Existing definitions of performance evaluation are largely tailored to accuracy and do not generalize to other metrics, leading to inconsistencies between participant-based and centralized evaluation. However, such discrepancies are inconsistent with the FL objective and lead to a wrong calculation of the metric. To address this issue, we examine the underlying reasons for these discrepancies and propose FLAM, a performance evaluation method based on aggregatable measures that yields the same results as centralized evaluation without the need for a global test dataset.

Federated Learning Model Evaluation Fairness-Aware Learning Machine Learning Benchmark Datasets Flames

Open paper Ask about it PDF

Abstract

Explore similar work

FLAM: Evaluating Model Performance with Aggregatable Measures in Federated Learning

Efficiently Distributed Federated Learning

Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning