[论文解读] Machine Teaching: A New Paradigm for Building Machine Learning Systems

Patrice Y. Simard, Saleema Amershi+9 more|arXiv (Cornell University)|Jul 21, 2017

Machine Learning and Data Classification参考文献 2被引用 76

一句话总结

本文主张把机器教学作为一种以教师生产力为焦点的学科，提出一个解耦的、基于接口的范式，扩展了能够构建 ML 系统的人员范围。它将与编程和软件工程的对比联想起来，以加速 ML 部署与协作。

ABSTRACT

The current processes for building machine learning systems require practitioners with deep knowledge of machine learning. This significantly limits the number of machine learning systems that can be created and has led to a mismatch between the demand for machine learning systems and the ability for organizations to build them. We believe that in order to meet this growing demand for machine learning systems we must significantly increase the number of individuals that can teach machines. We postulate that we can achieve this goal by making the process of teaching machines easy, fast and above all, universally accessible. While machine learning focuses on creating new algorithms and improving the accuracy of "learners", the machine teaching discipline focuses on the efficacy of the "teachers". Machine teaching as a discipline is a paradigm shift that follows and extends principles of software engineering and programming languages. We put a strong emphasis on the teacher and the teacher's interaction with data, as well as crucial components such as techniques and design principles of interaction and visualization. In this paper, we present our position regarding the discipline of machine teaching and articulate fundamental machine teaching principles. We also describe how, by decoupling knowledge about machine learning algorithms from the process of teaching, we can accelerate innovation and empower millions of new uses for machine learning models.

研究动机与目标

• 突出当前 ML 开发过程因过度依赖 ML 专家而带来的局限性。
• 提出把机器教学作为一种以教师生产力和与数据的交互为核心的学科。
• 主张通过标准化接口将教学与运行时 ML 算法解耦。
• 将机器教学与软件工程进行类比，以利用工具链和协作。
• 勾勒机器教学学科的原则、定义及路线图。

提出的方法

• 定义机器教学和机器教学研究，并将其与传统的 ML 研究区分开。
• 主张通过接口实现教学与 ML 算法的解耦，以使教学具备对运行时无关性。
• 将教学概念映射到编程类比（概念、特征、模式、分解）。
• 提出教学语言的系统需求，使其具备表达性、可扩展性，并与学习理论保持一致。
• 从编程中汲取的教训（分解、版本控制、API）作为 MT 工具与流程的指导原则。

实验结果

研究问题

• RQ1 什么是机器教学，它与传统的机器学习研究有何不同？
• RQ2 如何将教学从运行时 ML 算法中解耦以提高生产力和协作？
• RQ3 需要哪些接口和抽象来支持跨运行时的可扩展、可重用教学？
• RQ4 从编程中可以获得哪些组织和技术方面的类比，以指导 MT 工具和流程的发展？

主要发现

• 机器教学将 ML 模型构建重新定位为以教师为中心的活动，其度量与教师成本、可解释性和可扩展性相关。
• 教学可以通过表达输入/输出和模式的接口与 ML 算法解耦，从而实现对运行时无关的教学。
• 子概念、特征和模式有助于分解概念，便于教师进行更易操作和记录。
• 与编程的类比表明，MT 可以受益于版本控制、API、高级教学语言和模块化工具链。
• MT 范式旨在通过扩大能够构建 ML 系统的人员范围来民主化 ML，而不要求深度的 ML 专业知识。