【Author】
Wu, Yifu; Mendis, Gihan J.; Wei, Jin
【Source】IEEE INTERNET OF THINGS JOURNAL
【Abstract】In recent years, it has been observed the exponential growth of the Internet of Things (IoT) in different application fields, such as manufacturing and energy industry. To effectively fuse and process the tremendous amount of IoT sensing data timely, there is an urgent need to shift from a conventional centralized computing to a decentralized computing. However, there remain some essential technical challenges to develop effective decentralized computing methods in the context of IoT applications, including 1) the timely response, sufficient privacy preservation, and high security are normally required in IoT-related applications and 2) the biases and non-independent identically distributed (IID) properties potentially presented in the IoT sensing data. To address these challenges, in this article, we propose a decentralized deep learning paradigm with privacy-preservation and fast few-shot learning (DDLPF) by exploiting federated learning, metalearning, and blockchain techniques. In the simulation section, we evaluate the performance of our proposed DDLPF paradigm in different scenarios and compare it with other existing techniques.
【Keywords】Internet of Things; Deep learning; Data models; Computational modeling; Task analysis; Servers; Sensors; Blockchain; decentralized deep learning; few-shot learning; Internet of Things (IoT); metalearning; privacy preservation
【标题】DDLPF：用于物联网应用的实用去中心化深度学习范式
【摘要】近年来，人们观察到物联网 (IoT) 在制造业和能源行业等不同应用领域呈指数级增长。为了及时有效地融合和处理海量的物联网传感数据，迫切需要从传统的集中式计算转向分散式计算。然而，在物联网应用的背景下开发有效的去中心化计算方法仍然存在一些基本的技术挑战，包括 1）物联网相关应用通常需要及时响应、充分的隐私保护和高安全性；2）偏见和非-物联网传感数据中可能存在的独立同分布（IID）属性。为了应对这些挑战，在本文中，我们通过利用联邦学习、元学习和区块链技术，提出了一种具有隐私保护和快速少样本学习 (DDLPF) 的去中心化深度学习范式。在模拟部分，我们评估了我们提出的 DDLPF 范式在不同场景中的性能，并将其与其他现有技术进行了比较。
【关键词】物联网;深度学习；数据模型；计算建模；任务分析；服务器；传感器；区块链；去中心化深度学习；小样本学习；物联网（IoT）；元学习；隐私保护
评论