通过机器可检验的概念统一模型的可解释性和鲁棒性
Unifying Model Explainability and Robustness via Machine-Checkable Concepts
摘要：
随着深度神经网络（DNN）被越来越多的应用所采用，可解释性已经成为这些模型的关键需求。在许多现实世界的任务中，要求可解释性的主要原因之一是反过来评估预测鲁棒性，其中预测（即，类别标签）不符合它们各自的解释（例如，输入中概念的存在或不存在）被视为不可靠。然而，大多数（如果不是全部的话）用于检查澄清一致性的现有方法（例如，LIME、TCAV、显着图）需要大量的人工干预，这阻碍了它们的大规模部署。在本文中，我们提出了一个健壮性评估框架，其核心是使用机器可检查的概念的想法。我们的框架定义了大量的概念，DNN解释可以基于这些概念，并在测试时执行解释一致性检查，以评估预测的鲁棒性。这两个步骤都是以自动化的方式执行的，不需要任何人为干预，并且很容易扩展到具有大量类的数据集。在真实世界数据集和人类调查上的实验表明，我们的框架能够显着提高预测的鲁棒性：我们的框架标记为鲁棒的预测具有显着更高的准确性，并且对对抗性扰动更具鲁棒性。
英文摘要：
As deep neural networks (DNNs) get adopted in an ever-increasing number of applications, explainability has emerged as a crucial desideratum for these models. In many real-world tasks, one of the principal reasons for requiring explainability is to in turn assess prediction robustness, where predictions (i.e., class labels) that do not conform to their respective explanations (e.g., presence or absence of a concept in the input) are deemed to be unreliable. However, most, if not all, prior methods for checking explanation-conformity (e.g., LIME, TCAV, saliency maps) require significant manual intervention, which hinders their large-scale deployability. In this paper, we propose a robustness-assessment framework, at the core of which is the idea of using machine-checkable concepts. Our framework defines a large number of concepts that the DNN explanations could be based on and performs the explanation-conformity check at test time to assess prediction robustness. Both steps are executed in an automated manner without requiring any human intervention and are easily scaled to datasets with a very large number of classes. Experiments on real-world datasets and human surveys show that our framework is able to enhance prediction robustness significantly: the predictions marked to be robust by our framework have significantly higher accuracy and are more robust to adversarial perturbations.
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。
