Local Interpretable Model-Agnostic Explanations (LIME) is a popular method to perform interpretability of any kind of Machine Learning (ML) model. It explains one ML prediction at a time, by learning a simple linear model around the prediction. The model is trained on randomly generated data points, sampled from the training dataset distribution and weighted according to the distance from the reference point - the one being explained by LIME. Feature selection is applied to keep only the most important variables. LIME is widespread across different domains, although its instability - a single prediction may obtain different explanations - is one of the major shortcomings. This is due to the randomness in the sampling step, as well as to the flexibility in tuning the weights and determines a lack of reliability in the retrieved explanations, making LIME adoption problematic. In Medicine especially, clinical professionals trust is mandatory to determine the acceptance of an explainable algorithm, considering the importance of the decisions at stake and the related legal issues. In this paper, we highlight a trade-off between explanation's stability and adherence, namely how much it resembles the ML model. Exploiting our innovative discovery, we propose a framework to maximise stability, while retaining a predefined level of adherence. OptiLIME provides freedom to choose the best adherence-stability trade-off level and more importantly, it clearly highlights the mathematical properties of the retrieved explanation. As a result, the practitioner is provided with tools to decide whether the explanation is reliable, according to the problem at hand. We extensively test OptiLIME on a toy dataset - to present visually the geometrical findings - and a medical dataset. In the latter, we show how the method comes up with meaningful explanations both from a medical and mathematical standpoint.
翻译:本地解析模型- 模型- 数学解释( LIME ) 是一种常用的方法, 用来进行任何机器学习( ML) 模型的可解释性( LIME ) 。 它解释一次 ML 预测, 学习一个简单的线性模型 。 模型在随机生成的数据点上培训, 从培训数据集分布中抽样, 并根据参考点的距离加权 - LIME 解释。 特性选择仅用于保留最重要的变量 。 LIME 在不同领域广泛分布, 尽管其不稳定性( 一种广泛的预测可能获得不同的解释) 是主要缺陷之一 。 这是因为一次 ML 预测的随机性( ML ) 。 这解释了一个 ML 。 这是由于在测算重量时的随机性, 以及调控重时的灵活性 。 特别是, 临床专业人士的信任是确定一个可解释的算法, 考虑这些决定这些决定的稳定性和相关的法律问题。 在本文中, 我们强调解释的稳定性和遵守性能 。 定义一个数学解释方法与ML 模型的精确性水平 。 。 定义一个定义一个数据, 确定一个数据的稳定性, 我们提出一个定义一个稳定的稳定性, 确定一个定义一个定义一个数据, 和精确性, 我们的稳定性, 确定一个定义一个定义一个定义一个定义一个数据, 向后向后级的稳定性, 我们提出一个定义一个定义一个定义一个定义一个定义一个数据 。