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 2012.11067cs.LGcs.AIcs.LO
收藏

关于“为什么”?”和“为什么不呢?的讲解

On Relating 'Why?' and 'Why Not?' Explanations

Monash University(莫纳什大学);VMware Research(威睿研究院);ANITI;IRIT;CNRS(法国国家科学研究中心)

Alexey Ignatiev, Nina Narodytska, Nicholas Asher, Joao Marques-Silva

摘要:

机器学习(ML)模型的解释通常会解决“为什么?“问题。这样的解释可以与选择足以用于预测的特征值对相关。最近的工作调查了解决“为什么不?”的解释。”问题,即找到保证预测改变的特征值的改变。考虑到它们的目标,这两种解释ML模型预测的形式似乎大多不相关。然而,本文证明,否则,并建立了严格的正式关系之间的“为什么?”和“为什么不呢?”的解释。具体地说,本文证明,对于任何给定的情况下,“为什么?“解释是”为什么不呢?”的解释,反之亦然。此外,本文设计了新的算法提取和枚举两种形式的解释。

英文摘要:

Explanations of Machine Learning (ML) models often address a 'Why?' question. Such explanations can be related with selecting feature-value pairs which are sufficient for the prediction. Recent work has investigated explanations that address a 'Why Not?' question, i.e. finding a change of feature values that guarantee a change of prediction. Given their goals, these two forms of explaining predictions of ML models appear to be mostly unrelated. However, this paper demonstrates otherwise, and establishes a rigorous formal relationship between 'Why?' and 'Why Not?' explanations. Concretely, the paper proves that, for any given instance, 'Why?' explanations are minimal hitting sets of 'Why Not?' explanations and vice-versa. Furthermore, the paper devises novel algorithms for extracting and enumerating both forms of explanations.

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。

↑