arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.07985cs.AI
收藏

口译:用标准组织归因方法

Interpreting Interpretations: Organizing Attribution Methods by Criteria

Carnegie Mellon Univeristy(卡内基梅隆大学)

Zifan Wang, Piotr Mardziel, Anupam Datta, Matt Fredrikson

摘要:

在不同但相关的标准的推动下,越来越多的归因方法被开发出来以支持深度学习。虽然每一种方法都依赖于“重要性”概念的可解释性和我们对模式的可视化能力,但这些方法产生的解释往往不同。因此,视觉模型的输入属性无法提供任何人类对模型行为的理解。在这项工作中,我们扩展了人类可理解的概念的基础,其中归因可以被解释为超越“重要性”及其可视化;我们纳入了必要性和充分性的逻辑概念,以及比例的概念。我们定义计量学来表示这些概念作为属性的定量方面。这使我们能够比较不同方法产生的归因,并以新的方式解释它们:这种归因(或这种方法)在多大程度上代表了突出输入的必要性或充分性,以及在多大程度上是成比例的?我们评估了我们的措施上的集合的方法解释卷积神经网络(CNN)的图像分类。我们的结论是,一些归属方法更适合于解释的必要性,而其他的充分性,但没有一种方法总是最合适的两个方面。

英文摘要:

Motivated by distinct, though related, criteria, a growing number of attribution methods have been developed tointerprete deep learning. While each relies on the interpretability of the concept of "importance" and our ability to visualize patterns, explanations produced by the methods often differ. As a result, input attribution for vision models fail to provide any level of human understanding of model behaviour. In this work we expand the foundationsof human-understandable concepts with which attributionscan be interpreted beyond "importance" and its visualization; we incorporate the logical concepts of necessity andsufficiency, and the concept of proportionality. We definemetrics to represent these concepts as quantitative aspectsof an attribution. This allows us to compare attributionsproduced by different methods and interpret them in novelways: to what extent does this attribution (or this method)represent the necessity or sufficiency of the highlighted inputs, and to what extent is it proportional? We evaluate our measures on a collection of methods explaining convolutional neural networks (CNN) for image classification. We conclude that some attribution methods are more appropriate for interpretation in terms of necessity while others are in terms of sufficiency, while no method is always the most appropriate in terms of both.

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。

↑