对比中心化与去中心化联邦学习的性能权衡，揭示不同架构适用场景。
Centralized vs Decentralized Federated Learning: A trade-off performance analysis
- 通过实验比较三种联邦学习架构的训练效率与通信开销。
- 在MNIST数据集上验证去中心化模式通信量更低但收敛稍慢。
- 适合关注隐私保护与网络拓扑灵活性的系统设计者参考。
联邦学习（FL）作为一种新兴范式，在保护数据隐私的同时实现分布式边缘设备间的协同模型训练，尤其在物联网设备激增导致数据量剧增的背景下尤为重要。集中存储海量数据面临通信受限、隐私及合规等挑战。FL可分为中心化（CFL）、去中心化（DFL）和半去中心化（SDFL）三类，选择合适的架构需权衡应用需求。然而，现有研究极少对这三类架构进行实验性对比，以深入理解其优劣及各项性能指标间的权衡关系。本文填补该空白，基于Fedstellar模拟器、MNIST数据集与MLP分类器开展实验分析，系统评估不同架构在收敛速度、通信成本与鲁棒性等方面的差异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。