论文标题
RBX：基于区域的预测模型解释
RbX: Region-based explanations of prediction models
论文作者
论文摘要
我们介绍了一种基于区域的解释（RBX），这是一种新颖的模型 - 不合Snostic方法，可仅使用查询访问来从黑框预测模型中生成标量输出的局部解释。 RBX基于用于构建凸多物体的贪婪算法，该算法近似于特征空间的区域，其中模型预测接近某个目标点的预测。用户完全根据预测的规模来完全指定该区域，而不是在功能的规模上指定。该多层的几何形状 - 具体来说，逃脱多层的每个坐标的变化 - 量化了预测对每个特征的局部灵敏度。然后可以将这些“逃生距离”进行标准化，以通过本地重要性对特征进行排名。 RBX可以保证满足“稀疏公理”，该功能要求未进入预测模型的功能将其分配为零重要性。同时，实际数据示例和合成实验表明，与现有方法相比，RBX如何更容易检测到所有本地相关的特征。
We introduce region-based explanations (RbX), a novel, model-agnostic method to generate local explanations of scalar outputs from a black-box prediction model using only query access. RbX is based on a greedy algorithm for building a convex polytope that approximates a region of feature space where model predictions are close to the prediction at some target point. This region is fully specified by the user on the scale of the predictions, rather than on the scale of the features. The geometry of this polytope - specifically the change in each coordinate necessary to escape the polytope - quantifies the local sensitivity of the predictions to each of the features. These "escape distances" can then be standardized to rank the features by local importance. RbX is guaranteed to satisfy a "sparsity axiom," which requires that features which do not enter into the prediction model are assigned zero importance. At the same time, real data examples and synthetic experiments show how RbX can more readily detect all locally relevant features than existing methods.
