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 2105.07033cs.LG
收藏

因果:神经网络的层次概念解释

Cause and Effect: Hierarchical Concept-based Explanation of Neural Networks

Mohammad Nokhbeh Zaeem, Majid Komeili

摘要:

在许多情况下,人类决策是基于一些高级概念来解释的。在这项工作中,我们采取了一个步骤,在神经网络的可解释性,通过检查他们的内部表示或神经元的激活对概念。一个概念的特征在于一组具有共同特定特征的样本。我们提出了一个框架来检查存在的因果关系的概念(或其否定)和任务类。虽然以前的方法集中在一个概念的重要性,一个任务类,我们更进一步,并引入四个措施,定量确定因果关系的顺序。此外,我们提出了一种方法,用于构建一个层次的概念的形式,基于概念的决策树,它可以揭示如何在一个神经网络内的各种概念相互作用,预测输出类。通过实验,我们证明了所提出的方法在解释概念和神经网络的预测行为之间的因果关系,以及通过构建概念层次来确定不同概念之间的相互作用的有效性。

英文摘要:

In many scenarios, human decisions are explained based on some high-level concepts. In this work, we take a step in the interpretability of neural networks by examining their internal representation or neuron's activations against concepts. A concept is characterized by a set of samples that have specific features in common. We propose a framework to check the existence of a causal relationship between a concept (or its negation) and task classes. While the previous methods focus on the importance of a concept to a task class, we go further and introduce four measures to quantitatively determine the order of causality. Moreover, we propose a method for constructing a hierarchy of concepts in the form of a concept-based decision tree which can shed light on how various concepts interact inside a neural network towards predicting output classes. Through experiments, we demonstrate the effectiveness of the proposed method in explaining the causal relationship between a concept and the predictive behaviour of a neural network as well as determining the interactions between different concepts through constructing a concept hierarchy.

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。

↑