论文标题
现在您看到我（CME）：基于概念的模型提取
Now You See Me (CME): Concept-based Model Extraction
论文作者
论文摘要
深度神经网络（DNNS）在一系列任务上取得了出色的表现。进一步授权基于DNN的方法的关键步骤是提高其解释性。在这项工作中，我们介绍了CME：基于概念的模型提取框架，用于通过基于概念的提取模型来分析DNN模型。使用两种案例研究（DSPrites和Caltech UCSD鸟），我们证明了如何使用CME来（i）分析DNN模型（II）分析DNN在预测输出标签（III）时如何使用此概念信息的概念信息（III）可以通过进一步提高DNN预测性能的30％（我们可以改善案例研究）（对于一个案例研究）时，我们如何使用此概念信息（我们）如何使用此概念信息。概念）。
Deep Neural Networks (DNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering DNN-based approaches is improving their explainability. In this work we present CME: a concept-based model extraction framework, used for analysing DNN models via concept-based extracted models. Using two case studies (dSprites, and Caltech UCSD Birds), we demonstrate how CME can be used to (i) analyse the concept information learned by a DNN model (ii) analyse how a DNN uses this concept information when predicting output labels (iii) identify key concept information that can further improve DNN predictive performance (for one of the case studies, we showed how model accuracy can be improved by over 14%, using only 30% of the available concepts).
