论文标题
Baylime：贝叶斯本地解释的模型不足的解释
BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations
论文作者
论文摘要
考虑到确保算法透明度的紧迫性，可解释的AI（XAI）已成为AI研究的关键领域之一。在本文中，我们开发了一种新颖的贝叶斯扩展，以柠檬框架是XAI中使用最广泛的方法之一，我们称之为Baylime。与石灰相比，Baylime利用了先验知识和贝叶斯推理，以提高对单个预测的重复解释和内核环境的鲁棒性的一致性。 Baylime还表现出比最先进的（石灰，外形和Gradcam）更好的解释忠诚，其能够整合来自其他各种XAI技术的先验知识，以及验证和验证（V＆V）方法。我们通过理论分析和广泛的实验证明了Baylime的理想特性。
Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research. In this paper, we develop a novel Bayesian extension to the LIME framework, one of the most widely used approaches in XAI -- which we call BayLIME. Compared to LIME, BayLIME exploits prior knowledge and Bayesian reasoning to improve both the consistency in repeated explanations of a single prediction and the robustness to kernel settings. BayLIME also exhibits better explanation fidelity than the state-of-the-art (LIME, SHAP and GradCAM) by its ability to integrate prior knowledge from, e.g., a variety of other XAI techniques, as well as verification and validation (V&V) methods. We demonstrate the desirable properties of BayLIME through both theoretical analysis and extensive experiments.
