期刊名称：Bulletin of the Technical Committee on Data Engineering
出版年度：2018
卷号：41
期号：4
页码：46-53
出版社：IEEE Computer Society
摘要：As Machine Learning (ML) is becoming ubiquitously used within applications, developers need effectivesolutions to build and deploy their ML models across a large set of scenarios, from IoT devices to thecloud. Unfortunately, the current state of the art in model serving suggests to deliver predictions by runningmodels in containers. While this solution eases the operationalization of models, we observed thatit is not flexible enough to address the variety of ML scenarios encountered in large companies such asMicrosoft. In this paper, we will overview ML.NET—a recently open sourced ML pipeline framework—and describe how ML models written in ML.NET can be seamlessly integrated into applications. Finally,we will discuss how model serving can be cast to a database problem, and provide insights on our recentexperience in building a database optimizer for ML.NET pipelines..
