论文标题
对汽车的信任：探索在自动化机器学习系统中建立信任的信息需求
Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systems
论文作者
论文摘要
我们探索对相对较新的数据科学领域的信任：自动化机器学习（AUTOML）。在Automl中，AI方法用于通过自动工程功能，选择模型和优化超参数来生成和优化机器学习模型。在本文中，我们试图了解哪些信息会影响数据科学家对Automl产生的模型的信任？我们将信任运行是一种使用自动化方法生产的模型的愿意。我们报告了三项研究的结果 - 定性访谈，一个受控的实验和一项卡片分级任务 - 了解数据科学家在建立对汽车系统的信任的信息需求。我们发现，在Automl工具中包括透明度功能增加了用户信任和工具中的可理解性；在所有提出的功能中，在使用汽车工具建立信任时，模型性能指标和可视化是数据科学家的最重要信息。
We explore trust in a relatively new area of data science: Automated Machine Learning (AutoML). In AutoML, AI methods are used to generate and optimize machine learning models by automatically engineering features, selecting models, and optimizing hyperparameters. In this paper, we seek to understand what kinds of information influence data scientists' trust in the models produced by AutoML? We operationalize trust as a willingness to deploy a model produced using automated methods. We report results from three studies -- qualitative interviews, a controlled experiment, and a card-sorting task -- to understand the information needs of data scientists for establishing trust in AutoML systems. We find that including transparency features in an AutoML tool increased user trust and understandability in the tool; and out of all proposed features, model performance metrics and visualizations are the most important information to data scientists when establishing their trust with an AutoML tool.
