基于概念的自动推理
Towards Automatic Concept-based Explanations
摘要：
随着越来越多的机器学习（ML）模型被部署并广泛用于做出重要决策，可解释性已成为一个重要的研究课题。目前的大多数解释方法通过特征重要性分数来提供解释，该分数识别对每个输入重要的特征。然而，如何系统地总结和解释这样的每样本特征重要性分数本身是具有挑战性的。在这项工作中，我们提出了原则和必要的\emph{concept}为基础的解释，它超越了每个样本的功能，以确定更高层次的人类可理解的概念，适用于整个数据集。我们开发了一个新的算法，ACE，自动提取视觉概念。我们的系统实验表明，\alg发现的概念是人类有意义的，连贯的和重要的神经网络的预测。
英文摘要：
Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature importance scores, which identify features that are important for each individual input. However, how to systematically summarize and interpret such per sample feature importance scores itself is challenging. In this work, we propose principles and desiderata for \emph{concept} based explanation, which goes beyond per-sample features to identify higher-level human-understandable concepts that apply across the entire dataset. We develop a new algorithm, ACE, to automatically extract visual concepts. Our systematic experiments demonstrate that \alg discovers concepts that are human-meaningful, coherent and important for the neural network's predictions.
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。
