arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.03012cs.AIcs.CVcs.HCstat.ML
收藏

一种解释并不适用于所有解释:AI可解释性技术的工具包和分类

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

IBM Research(IBM研究院)
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovi… 展开作者

Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilović, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang

摘要:

随着人工智能和机器学习算法进一步进入社会,多个利益相关者越来越多地要求这些算法解释其输出。与此同时,这些利益相关者,无论是受影响的公民、政府监管机构、领域专家还是系统开发人员,都对解释提出了不同的要求。为了满足这些需求,我们引入了AI Explainability 360(http://aix360.mybluemix.net/),这是一个开源软件工具包,具有八种不同的最先进的解释方法和两个评估指标。同样重要的是,我们提供了一个分类法,以帮助需要解释的实体导航的解释方法的空间,不仅在工具包中,而且在更广泛的文献解释。对于数据科学家和工具包的其他用户,我们已经实现了一个可扩展的软件架构,该架构根据方法在AI建模管道中的位置来组织方法。我们还讨论了增强功能,以使研究创新更接近解释的消费者,从简化的,更容易访问的算法版本,到教程和交互式Web演示,以向不同的受众和应用领域介绍人工智能的可解释性。总之,我们的工具包和分类法可以帮助识别需要更多可解释性方法的差距,并提供一个平台来整合它们。

英文摘要:

As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, present different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360 (http://aix360.mybluemix.net/), an open-source software toolkit featuring eight diverse and state-of-the-art explainability methods and two evaluation metrics. Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. We also discuss enhancements to bring research innovations closer to consumers of explanations, ranging from simplified, more accessible versions of algorithms, to tutorials and an interactive web demo to introduce AI explainability to different audiences and application domains. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed.

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。

↑