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 2109.09160cs.HCcs.AI
收藏

分类规则理解中视觉因素的探索与验证

An Exploration And Validation of Visual Factors in Understanding Classification Rule Sets

New York University(纽约大学)

Jun Yuan, Oded Nov, Enrico Bertini

摘要:

规则集通常用于机器学习(ML)中,作为在需要透明度和可理解性的设置中传达模型逻辑的一种方式。规则集通常以基于文本的逻辑语句(规则)列表的形式呈现。令人惊讶的是,到目前为止,在探索视觉替代方案来呈现规则方面的工作有限。在本文中,我们探讨了设计规则的替代表示的想法,专注于一些视觉因素,我们认为有一个积极的影响规则的可读性和理解。然后,我们提出了一个用户研究探索其影响。结果表明,一些设计因素对读者处理规则的效率有很大影响,而对准确性的影响最小。这项工作可以帮助从业者在使用规则作为理解ML模型的通信策略时采用更有效的解决方案。

英文摘要:

Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logical statements (rules). Surprisingly, to date there has been limited work on exploring visual alternatives for presenting rules. In this paper, we explore the idea of designing alternative representations of rules, focusing on a number of visual factors we believe have a positive impact on rule readability and understanding. We then presents a user study exploring their impact. The results show that some design factors have a strong impact on how efficiently readers can process the rules while having minimal impact on accuracy. This work can help practitioners employ more effective solutions when using rules as a communication strategy to understand ML models.

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。

↑