论局部替代解释者的解释目标界定问题
On the overlooked issue of defining explanation objectives for local-surrogate explainers
摘要：
解释机器学习模型预测的局部替代方法具有吸引人的特性，例如模型不可知性和建模灵活性。有几种方法符合这一描述并共享这一目标。然而，尽管他们有共同的总体程序，但他们提出了不同的目标，从黑匣子中提取了不同的信息，因此产生了不同的解释，这些解释通常是无法比拟的。在这项工作中，我们回顾了多种方法之间的相似性和差异，特别关注它们从模型中提取的信息，因为这对输出有很大的影响：解释。我们讨论了缺乏协议的影响，和清晰度，在方法的目标之间的研究和实践的可解释性。
英文摘要：
Local surrogate approaches for explaining machine learning model predictions have appealing properties, such as being model-agnostic and flexible in their modelling. Several methods exist that fit this description and share this goal. However, despite their shared overall procedure, they set out different objectives, extract different information from the black-box, and consequently produce diverse explanations, that are -- in general -- incomparable. In this work we review the similarities and differences amongst multiple methods, with a particular focus on what information they extract from the model, as this has large impact on the output: the explanation. We discuss the implications of the lack of agreement, and clarity, amongst the methods' objectives on the research and practice of explainability.
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。
