arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.15465cs.LGcs.AIcs.HC
收藏

可解释性,然后呢?编辑机器学习模型以反映人类知识和价值观

Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values

Georgia Institute of Technology(佐治亚理工学院);University of Washington(华盛顿大学);Microsoft Research(微软研究院);NYU Langone Health(纽约大学朗格尼医学中心)

Zijie J. Wang, Alex Kale, Harsha Nori, Peter Stella, Mark E. Nunnally, Duen Horng Chau, Mihaela Vorvoreanu, Jennifer Wortman Vaughan, Rich Caruana

摘要:

机器学习(ML)可解释性技术可以揭示模型用来进行预测的数据中的不良模式-一旦部署,可能会造成危害。然而,如何采取行动解决这些问题并不总是很清楚。在ML和人机交互研究人员、医生和数据科学家之间的合作中,我们开发了GAM Changer,这是第一个交互式系统,可以帮助领域专家和数据科学家轻松、负责任地编辑广义加性模型(GAM)并修复有问题的模式。通过新颖的交互技术,我们的工具将可解释性转化为行动-使用户能够分析,验证和调整模型行为与他们的知识和价值观。医生已经开始使用我们的工具来研究和修复肺炎和败血症风险预测模型,7位在不同领域工作的数据科学家的评估强调,我们的工具易于使用,满足他们的模型编辑需求,并适合他们当前的工作流程。我们的工具采用现代Web技术构建,在用户的Web浏览器或计算笔记本中本地运行,降低了使用障碍。GAM Changer可在以下公开演示链接中获得:https://interpret.ml/gam-changer。

英文摘要:

Machine learning (ML) interpretability techniques can reveal undesirable patterns in data that models exploit to make predictions--potentially causing harms once deployed. However, how to take action to address these patterns is not always clear. In a collaboration between ML and human-computer interaction researchers, physicians, and data scientists, we develop GAM Changer, the first interactive system to help domain experts and data scientists easily and responsibly edit Generalized Additive Models (GAMs) and fix problematic patterns. With novel interaction techniques, our tool puts interpretability into action--empowering users to analyze, validate, and align model behaviors with their knowledge and values. Physicians have started to use our tool to investigate and fix pneumonia and sepsis risk prediction models, and an evaluation with 7 data scientists working in diverse domains highlights that our tool is easy to use, meets their model editing needs, and fits into their current workflows. Built with modern web technologies, our tool runs locally in users' web browsers or computational notebooks, lowering the barrier to use. GAM Changer is available at the following public demo link: https://interpret.ml/gam-changer.

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。

↑