【Author】
Cao, Mingrui; Cao, Bin; Hong, Wei; Zhao, Zhongyuan; Bai, Xiang; Zhang, Lei
【Source】IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021)
【Abstract】Due to the distributed characteristics of Federated Learning (FL), the vulnerability of global model and coordination of devices are the main obstacle. As a promising solution of decentralization, scalability and security, leveraging blockchain in FL has attracted much attention in recent years. However, the traditional consensus mechanisms designed for blockchain like Proof of Work (PoW) would cause extreme resource consumption, which reduces the efficiency of FL greatly, especially when the participating devices are wireless and resource-limited. In order to address device asynchrony and anomaly detection in FL while avoiding the extra resource consumption caused by blockchain, this paper introduces a framework for empowering FL using Direct Acyclic Graph (DAG)-based blockchain systematically (DAG-FL). Accordingly, DAG-FL is first introduced from a three-layer architecture in details, and then two algorithms DAG-FL Controlling and DAG-FL Updating are designed running on different nodes to elaborate the operation of DAG-FL consensus mechanism. The extensive simulations show that DAG-FL can achieve the better performance in terms of training efficiency and model accuracy compared with the typical existing on-device federated learning systems as the benchmarks.
【标题】DAG-FL：基于直接无环图的区块链赋能设备上联邦学习
【摘要】由于联邦学习（FL）的分布式特性，全局模型的脆弱性和设备的协调性是主要障碍。作为去中心化、可扩展性和安全性的有前途的解决方案，在 FL 中利用区块链近年来备受关注。然而，像工作量证明（PoW）这样为区块链设计的传统共识机制会导致资源消耗极大，大大降低了 FL 的效率，尤其是在参与设备是无线且资源有限的情况下。为了解决 FL 中的设备异步和异常检测问题，同时避免区块链带来的额外资源消耗，本文介绍了一种系统地使用基于直接无环图 (DAG) 的区块链 (DAG-FL) 赋能 FL 的框架。据此，首先从三层架构详细介绍 DAG-FL，然后设计了运行在不同节点上的 DAG-FL Controlling 和 DAG-FL Updating 两种算法来详细阐述 DAG-FL 共识机制的运行。大量的仿真表明，与典型的现有设备上联邦学习系统作为基准相比，DAG-FL 在训练效率和模型准确性方面可以取得更好的性能。
评论