arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.16157cs.LGcs.DC
收藏

共识学习:一种新颖的去中心化集成学习范式

Consensus learning: A novel decentralised ensemble learning paradigm

Flare Research(弗拉雷研究所)

Horia Magureanu, Naïri Usher

AI总结:

本文提出共识学习范式,将经典集成方法与点对点共识协议结合,在保护数据隐私和抵御拜占庭攻击的同时实现去中心化分布式学习,并通过理论分析和数值模拟验证其鲁棒性。

摘要:

近年来,大规模机器学习模型的广泛采用凸显了对分布式计算在效率和可扩展性方面的需求。本工作引入了一种新颖的分布式机器学习范式——共识学习——它将经典集成方法与部署在点对点系统中的共识协议相结合。这些算法由两个阶段组成:首先,参与者开发各自的模型,并对任何新的数据输入提交预测;其次,个体预测被用作通信阶段的输入,该阶段由共识协议管理。共识学习在确保用户数据隐私的同时,也继承了底层共识机制中针对拜占庭攻击的安全措施。我们针对一种特定的共识协议提供了详细的理论分析,并将共识学习集成与中心化集成学习算法的性能进行了比较。讨论辅以多种数值模拟,这些模拟描述了算法在面对拜占庭参与者时的鲁棒性。

英文摘要:

The widespread adoption of large-scale machine learning models in recent years highlights the need for distributed computing for efficiency and scalability. This work introduces a novel distributed machine learning paradigm -- \emph{consensus learning} -- which combines classical ensemble methods with consensus protocols deployed in peer-to-peer systems. These algorithms consist of two phases: first, participants develop their models and submit predictions for any new data inputs; second, the individual predictions are used as inputs for a communication phase, which is governed by a consensus protocol. Consensus learning ensures user data privacy, while also inheriting the safety measures against Byzantine attacks from the underlying consensus mechanism. We provide a detailed theoretical analysis for a particular consensus protocol and compare the performance of the consensus learning ensemble with centralised ensemble learning algorithms. The discussion is supplemented by various numerical simulations, which describe the robustness of the algorithms against Byzantine participants.

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。

↑