arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.12277cs.LGcs.AIcs.CV
收藏

一种改进解释性和保真度的LIME扩展

An Extension of LIME with Improvement of Interpretability and Fidelity

Lenovo Research(联想研究院)

Sheng Shi, Yangzhou Du, Wei Fan

摘要:

虽然深度学习在人工智能(AI)领域取得了重大成就,但缺乏透明度限制了其在各个垂直领域的广泛应用。可解释性不仅是人工智能与现实世界之间的门户,也是检测模型缺陷和数据偏差的强大功能。局部可解释模型不可知解释(LIME)是一种被广泛接受的技术,它通过在预测实例周围局部学习可解释模型来忠实地解释任何分类器的预测。作为LIME的扩展,本文提出了一种高解释性和高保真度的局部解释方法,称为局部解释使用特征相关采样和非线性近似(LEDSNA)。给出了一个实例,LEDSNA增强解释性的特征采样与内在的依赖性。此外,LEDSNA通过逼近局部决策的非线性边界,提高了局部解释的保真度。我们评估我们的方法在图像域和文本域的分类任务。实验表明,LEDSNA的解释后箱模型实现了更好的性能比原来的LIME在可解释性和保真度。

英文摘要:

While deep learning makes significant achievements in Artificial Intelligence (AI), the lack of transparency has limited its broad application in various vertical domains. Explainability is not only a gateway between AI and real world, but also a powerful feature to detect flaw of the models and bias of the data. Local Interpretable Model-agnostic Explanation (LIME) is a widely-accepted technique that explains the prediction of any classifier faithfully by learning an interpretable model locally around the predicted instance. As an extension of LIME, this paper proposes an high-interpretability and high-fidelity local explanation method, known as Local Explanation using feature Dependency Sampling and Nonlinear Approximation (LEDSNA). Given an instance being explained, LEDSNA enhances interpretability by feature sampling with intrinsic dependency. Besides, LEDSNA improves the local explanation fidelity by approximating nonlinear boundary of local decision. We evaluate our method with classification tasks in both image domain and text domain. Experiments show that LEDSNA's explanation of the back-box model achieves much better performance than original LIME in terms of interpretability and fidelity.

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。

↑