Sample based Explanations via Generalized Representers

We propose a general class of sample based explanations of machine learning models, which we term generalized representers. To measure the effect of a training sample on a model's test prediction, generalized representers use two components: a global sample importance that quantifies the importance of the training point to the model and is invariant to test samples, and a local sample importance that measures similarity between the training sample and the test point with a kernel. A key contribution of the paper is to show that generalized representers are the only class of sample based explanations satisfying a natural set of axiomatic properties. We discuss approaches to extract global importances given a kernel, and also natural choices of kernels given modern non-linear models. As we show, many popular existing sample based explanations could be cast as generalized representers with particular choices of kernels and approaches to extract global importances. Additionally, we conduct empirical comparisons of different generalized representers on two image and two text classification datasets.

我们提出了一类基于样本的机器学习模型解释的通用方法，我们称之为广义表示器。为了衡量一个训练样本对模型测试预测的影响，广义表示器使用两个组件：全局样本重要性，它量化训练点对模型的重要性，并且对测试样本是不变的；以及局部样本重要性，它使用核函数来衡量训练样本和测试点之间的相似性。本文的一个关键贡献是表明广义表示器是唯一满足一组自然公理性质的基于样本的解释类别。我们讨论了在给定核函数的情况下提取全局重要性的方法，以及在给定现代非线性模型的情况下核函数的自然选择。正如我们所展示的，许多现有的流行的基于样本的解释都可以被视为具有特定核函数选择和提取全局重要性方法的广义表示器。此外，我们在两个图像和两个文本分类数据集上对不同的广义表示器进行了实证比较。