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 2005.14080cs.DCcs.AIcs.LG
收藏

将机器学习转化为面向最终用户的服务

Parallelizing Machine Learning as a Service for the End-User

University of Bologna(博洛尼亚大学);University of Modena and Reggio Emilia(摩德纳-雷焦艾米利亚大学)

Daniela Loreti, Marco Lippi, Paolo Torroni

摘要:

随着机器学习应用变得越来越普遍,经过充分训练的系统越来越多地提供给公众,允许最终用户使用自己的数据提交查询,并有效地检索结果。随着这些服务的日益复杂,一个新的挑战是如何扩大规模,以满足不断增长的用户基础。在本文中,我们提出了一个分布式架构,可以利用它来并行化一个典型的ML系统管道。我们提出了一个案例研究组成的文本挖掘服务,并讨论了如何将该方法推广到许多类似的应用程序。我们证明了通过广泛的实验评估的方式的分布式架构的计算增益的意义。

英文摘要:

As ML applications are becoming ever more pervasive, fully-trained systems are made increasingly available to a wide public, allowing end-users to submit queries with their own data, and to efficiently retrieve results. With increasingly sophisticated such services, a new challenge is how to scale up to evergrowing user bases. In this paper, we present a distributed architecture that could be exploited to parallelize a typical ML system pipeline. We propose a case study consisting of a text mining service and discuss how the method can be generalized to many similar applications. We demonstrate the significance of the computational gain boosted by the distributed architecture by way of an extensive experimental evaluation.

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。

↑