一句话：提出FBFL，以场协调和宏编程实现分布式选举与自组织分层联邦学习，缓解non-IID并提升鲁棒性。
联邦学习在隐私敏感领域应用广泛，但设备数据常因空间分布呈non-IID，导致模型性能下降，且集中式架构带来瓶颈与单点故障。本文提出FBFL，利用宏编程与场协调构建联邦学习方案：通过分布式空间leader选举实现个性化，缓解non-IID；并借助宏编程模式构建自组织分层架构，支持子区域专用模型。论文形式化FBFL，并在MNIST、FashionMNIST、Extended MNIST上评估。结果显示，IID下性能与FedAvg相当；non-IID下优于FedAvg、FedProx和Scaffold；其自组织分层架构还表现出对服务器故障的韧性。
In the last years, Federated learning (FL) has become a popular solution to train machine learning models in domains with high privacy concerns. However, FL scalability and performance face significant challenges in real-world deployments where data across devices are non-independently and identically distributed (non-IID). The heterogeneity in data distribution frequently arises from spatial distribution of devices, leading to degraded model performance in the absence of proper handling. Additionally, FL typical reliance on centralized architectures introduces bottlenecks and single-point-of-failure risks, particularly problematic at scale or in dynamic environments. To close this gap, we propose Field-Based Federated Learning (FBFL), a novel approach leveraging macroprogramming and field coordination to address these limitations through: (i) distributed spatial-based leader election for personalization to mitigate non-IID data challenges; and (ii) construction of a self-organizing, hierarchical architecture using advanced macroprogramming patterns. Moreover, FBFL not only overcomes the aforementioned limitations, but also enables the development of more specialized models tailored to the specific data distribution in each subregion. This paper formalizes FBFL and evaluates it extensively using MNIST, FashionMNIST, and Extended MNIST datasets. We demonstrate that, when operating under IID data conditions, FBFL performs comparably to the widely-used FedAvg algorithm. Furthermore, in challenging non-IID scenarios, FBFL not only outperforms FedAvg but also surpasses other state-of-the-art methods, namely FedProx and Scaffold, which have been specifically designed to address non-IID data distributions. Additionally, we showcase the resilience of FBFL's self-organizing hierarchical architecture against server failures.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@article{abs-2502-08577,
title = {FBFL: A Field-Based Coordination Approach for Data Heterogeneity in Federated Learning},
author = {Davide Domini and Gianluca Aguzzi and Lukas Esterle and Mirko Viroli},
journal = {Logical Methods in Computer Science},
volume = {Volume 22, Issue 1},
year = {2026},
doi = {10.46298/lmcs-22(1:19)2026}
}