论文标题
石灰的扩展，并提高可解释性和忠诚度
An Extension of LIME with Improvement of Interpretability and Fidelity
论文作者
论文摘要
尽管深度学习在人工智能（AI）方面取得了重大成就，但缺乏透明度限制了其在各种垂直领域的广泛应用。解释性不仅是AI和现实世界之间的网关，而且是检测模型和数据偏置缺陷的强大功能。局部可解释的模型不足的解释（Lime）是一种广泛接受的技术，可以通过在预测的实例上在本地学习可解释的模型来忠实地解释任何分类器的预测。作为石灰的扩展，本文提出了使用特征依赖性采样和非线性近似（LEDSNA）的高解释性和高保真局部解释方法，称为局部解释。鉴于正在解释实例，LEDSNA通过具有内在依赖性的特征采样来增强可解释性。此外，LEDSNA通过近似局部决策的非线性边界来改善局部解释忠诚度。我们通过图像域和文本域中的分类任务评估我们的方法。实验表明，LEDSNA对后盒模型的解释在可解释性和忠诚方面，其表现要比原始石灰更好。
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.
