【Author】
Toyoda, Kentaroh; Zhao, Jun; Zhang, Allan Neng Sheng; Mathiopoulos, P. Takis
【Abstract】Federated learning (FL) is a promising decentralized deep learning technique that allows users to collaboratively update models without sharing their own data. However, due to its decentralized nature, no one can monitor workers' behavior, and they may thus deviate protocols (e.g., participating without updating any models). To solve this problem, many researchers have proposed blockchain-enabled FL to reward workers (or users) with cryptocurrencies to encourage workers to follow the protocols. However, there is a lack of theoretical discussions concerning how such rewards impact workers' behavior and how much should be given to workers. In this article, we propose a mechanism-design-oriented FL protocol on a public blockchain network. Mechanism design (MD) is often used to make a rule intended to achieve a specific goal. With MD in mind, we introduce the concept of competition into blockchain-based FL so that only workers who have contributed well can obtain rewards, which naturally prevents workers from deviating from the protocol. We then mathematically answer the following questions with contest theory, a novel field of study in economics: i) What behavior will workers take?; ii) how much effort should workers exert to maximize their profits?; iii) how many workers should be rewarded?; and iv) what is the best proportion for reward distribution?
【Keywords】Blockchain; Biological system modeling; Data models; Cryptography; Smart contracts; Task analysis; Protocols; Federated learning; decentralized deep learning; blockchain; mechanism design; contest theory
【摘要】联邦学习 (FL) 是一种很有前途的去中心化深度学习技术，它允许用户在不共享自己的数据的情况下协作更新模型。然而，由于其去中心化的性质，没有人可以监控工人的行为，因此他们可能会偏离协议（例如，在不更新任何模型的情况下参与）。为了解决这个问题，许多研究人员提出了支持区块链的 FL 来用加密货币奖励工人（或用户），以鼓励工人遵守协议。然而，关于这种奖励如何影响工人的行为以及应该给予工人多少，缺乏理论讨论。在本文中，我们在公共区块链网络上提出了一种面向机制设计的 FL 协议。机制设计 (MD) 通常用于制定旨在实现特定目标的规则。考虑到 MD，我们在基于区块链的 FL 中引入了竞争的概念，只有贡献好的工人才能获得奖励，这自然地防止了工人偏离协议。然后，我们用竞赛理论（经济学的一个新研究领域）从数学上回答以下问题：i）工人会采取什么行为？ ii) 工人应该付出多少努力才能使他们的利润最大化？ iii) 应该奖励多少工人？ iv) 奖励分配的最佳比例是多少？
【关键词】区块链；生物系统建模；数据模型；密码学；智能合约；任务分析；协议；联邦学习；去中心化深度学习；区块链；机制设计；竞争理论
评论