论文标题
解释所有神经网络的差异耐受因素
Variance Tolerance Factors For Interpreting ALL Neural Networks
论文作者
论文摘要
黑匣子模型仅为深度学习任务提供结果，并且缺乏有关如何获得这些结果的信息细节。除了输入变量与输出相关之外，除了为什么相关之外，对于将预测转化为实验室实验至关重要，或捍卫在审查下的模型预测。在本文中，我们提出了一种一般理论，该理论定义了受影响功能启发的差异公差因子（VTF），通过对特征的重要性进行排名，并在黑匣子神经网络的背景下解释特征，并构建一个由基本模型和功能模型组成的新型体系结构，以探索包含所有良好成绩成熟的神经网络中的RashOmon集合。 Rashomon集中的两个功能重要性排名方法和基于VTF的功能选择方法的两个功能被创建和探索。对合成和基准数据集进行了详尽的评估，该方法适用于两个现实世界中的例子，预测了非晶体金纳米颗粒的形成和化学毒性1793暴露于原生动物纤毛的芳族化合物40小时。
Black box models only provide results for deep learning tasks, and lack informative details about how these results were obtained. Knowing how input variables are related to outputs, in addition to why they are related, can be critical to translating predictions into laboratory experiments, or defending a model prediction under scrutiny. In this paper, we propose a general theory that defines a variance tolerance factor (VTF) inspired by influence function, to interpret features in the context of black box neural networks by ranking the importance of features, and construct a novel architecture consisting of a base model and feature model to explore the feature importance in a Rashomon set that contains all well-performing neural networks. Two feature importance ranking methods in the Rashomon set and a feature selection method based on the VTF are created and explored. A thorough evaluation on synthetic and benchmark datasets is provided, and the method is applied to two real world examples predicting the formation of noncrystalline gold nanoparticles and the chemical toxicity 1793 aromatic compounds exposed to a protozoan ciliate for 40 hours.
