arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.12410cs.LGcs.AI
收藏

基于邻近性的自联邦学习

Proximity-based Self-Federated Learning

University of Bologna(博洛尼亚大学);Aarhus University(奥胡斯大学)

Davide Domini, Gianluca Aguzzi, Nicolas Farabegoli, Mirko Viroli, Lukas Esterle

AI总结:

提出一种基于地理邻近性和数据分布的完全分布式自联邦学习策略,无需中央服务器和原始数据交换,通过客户端间模型共享与调整,创建多个专业化联邦,提升模型对不同区域特征的适应性,并在知名数据集上验证其优于传统集中式联邦学习。

摘要:

在机器学习的最新进展中,联邦学习允许分布式客户端网络在不共享本地数据的情况下协作开发全局模型。该技术旨在保护隐私,应对传统集中式学习方法中的脆弱性。传统联邦学习方法通常依赖中央服务器来协调各客户端的模型训练,旨在所有节点上统一复制相同的模型。然而,这些方法忽视了大型网络中地理和本地数据差异的重要性,可能影响模型的有效性和适用性。此外,依赖中央服务器可能成为大型网络的瓶颈,例如边缘计算所推动的网络。我们的论文提出了一种新颖的、完全分布式的联邦学习策略,称为基于邻近性的自联邦学习,该策略使客户端能够根据其地理邻近性和数据分布,在不交换原始数据的情况下,自组织地创建多个客户端联邦。实际上,与传统算法不同,我们的方法鼓励客户端根据地理邻近性和模型准确性,与邻近节点共享和调整其模型。该方法不仅解决了不同数据分布带来的限制,还增强了模型对不同区域特征的适应性,为每个联邦创建专门的模型。我们通过在知名数据集上的模拟展示了我们方法的有效性,证明了其相对于传统集中式联邦学习框架的优越性。

英文摘要:

In recent advancements in machine learning, federated learning allows a network of distributed clients to collaboratively develop a global model without needing to share their local data. This technique aims to safeguard privacy, countering the vulnerabilities of conventional centralized learning methods. Traditional federated learning approaches often rely on a central server to coordinate model training across clients, aiming to replicate the same model uniformly across all nodes. However, these methods overlook the significance of geographical and local data variances in vast networks, potentially affecting model effectiveness and applicability. Moreover, relying on a central server might become a bottleneck in large networks, such as the ones promoted by edge computing. Our paper introduces a novel, fully-distributed federated learning strategy called proximity-based self-federated learning that enables the self-organised creation of multiple federations of clients based on their geographic proximity and data distribution without exchanging raw data. Indeed, unlike traditional algorithms, our approach encourages clients to share and adjust their models with neighbouring nodes based on geographic proximity and model accuracy. This method not only addresses the limitations posed by diverse data distributions but also enhances the model's adaptability to different regional characteristics creating specialized models for each federation. We demonstrate the efficacy of our approach through simulations on well-known datasets, showcasing its effectiveness over the conventional centralized federated learning framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑