Federated data analytics: A study on linear models
Federated data analytics: A study on linear models
复制标题
DOI：
10.1080/24725854.2022.2157912
复制
发表时间：
2022-06
影响因子：
2.6
通讯作者：
Xubo Yue;R. Kontar;Ana María Estrada Gómez
中科院分区：
文献类型：
--
作者：
Xubo Yue;R. Kontar;Ana María Estrada Gómez
随着边缘设备变得越来越强大，数据分析正逐渐从集中式转向分散式，利用边缘计算资源在本地处理更多数据。这种分析机制被称为联邦数据分析（FDA）。尽管FDA最近取得了成功，但大多数文献只关注深度神经网络。在这项工作中，我们退一步开发FDA治疗最基本的统计模型之一：线性回归。我们的处理是建立在分层模型之上的，它允许跨多个组借用力量。为此，我们提出了两种联邦层次模型结构，提供跨设备的共享表示，以促进信息共享。值得注意的是，我们提出的框架能够提供不确定性量化、变量选择、假设检验和对新的未知数据的快速适应。我们在一系列实际应用中验证了我们的方法，包括飞机发动机的状态监测。结果表明，我们对线性模型的FDA处理可以作为联邦算法未来发展的竞争性基准模型。
Abstract As edge devices become increasingly powerful, data analytics are gradually moving from a centralized to a decentralized regime where edge computing resources are exploited to process more of the data locally. This regime of analytics is coined as Federated Data Analytics (FDA). Despite the recent success stories of FDA, most literature focuses exclusively on deep neural networks. In this work, we take a step back to develop an FDA treatment for one of the most fundamental statistical models: linear regression. Our treatment is built upon hierarchical modeling that allows borrowing strength across multiple groups. To this end, we propose two federated hierarchical model structures that provide a shared representation across devices to facilitate information sharing. Notably, our proposed frameworks are capable of providing uncertainty quantification, variable selection, hypothesis testing, and fast adaptation to new unseen data. We validate our methods on a range of real-life applications, including condition monitoring for aircraft engines. The results show that our FDA treatment for linear models can serve as a competing benchmark model for the future development of federated algorithms.