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 2307.07066cs.CRcs.CEcs.DCcs.LG
收藏

训练证明(PoT):利用加密挖矿算力进行分布式 AI 训练

Proof of Training (PoT): Harnessing Crypto Mining Power for Distributed AI Training

King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);Zayed University(扎耶德大学)

Peihao Li

AI总结:

针对 AI 与加密挖矿融合中的三大挑战,本文提出基于 PBFT 共识的 PoT 协议,并通过去中心化训练网络验证其在吞吐、鲁棒性与安全上的潜力。

摘要:

在人工智能(AI)与加密挖矿相融合的新兴趋势中,我们识别出造成这两个领域之间鸿沟的三大主要挑战。为弥合这一鸿沟,我们提出了训练证明(PoT)协议,该方法结合了 AI 与区块链技术的优势。PoT 协议采用实用拜占庭容错(PBFT)共识机制来同步全局状态。为评估协议设计的性能,我们给出了一个采用 PoT 协议的去中心化训练网络(DTN)实现。结果表明,该协议在任务吞吐量、系统鲁棒性和网络安全性方面展现出相当大的潜力。

英文摘要:

In the midst of the emerging trend of integrating artificial intelligence (AI) with crypto mining, we identify three major challenges that create a gap between these two fields. To bridge this gap, we introduce the proof-of-training (PoT) protocol, an approach that combines the strengths of both AI and blockchain technology. The PoT protocol utilizes the practical Byzantine fault tolerance (PBFT) consensus mechanism to synchronize global states. To evaluate the performance of the protocol design, we present an implementation of a decentralized training network (DTN) that adopts the PoT protocol. Our results indicate that the protocol exhibits considerable potential in terms of task throughput, system robustness, and network security.

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。

↑