Many learning algorithms such as kernel machines, nearest neighbors, clustering, or anomaly detection, are based on distances or similarities. Before similarities are used for training an actual machine learning model, we would like to verify that they are bound to meaningful patterns in the data. In this paper, we propose to make similarities interpretable by augmenting them with an explanation. We develop BiLRP, a scalable and theoretically founded method to systematically decompose the output of an already trained deep similarity model on pairs of input features. Our method can be expressed as a composition of LRP explanations, which were shown in previous works to scale to highly nonlinear models. Through an extensive set of experiments, we demonstrate that BiLRP robustly explains complex similarity models, e.g., built on VGG-16 deep neural network features. Additionally, we apply our method to an open problem in digital humanities: detailed assessment of similarity between historical documents, such as astronomical tables. Here again, BiLRP provides insight and brings verifiability into a highly engineered and problem-specific similarity model.

中文翻译：

---

构建和解释深度相似模型


许多学习算法（例如内核机、最近邻居、聚类或异常检测）都是基于距离或相似性。在使用相似性来训练实际的机器学习模型之前，我们希望验证它们是否与数据中有意义的模式绑定。在本文中，我们建议通过解释来增强相似性，从而使相似性变得可解释。我们开发了 BiLRP，这是一种可扩展且有理论基础的方法，可以系统地分解已训练的深度相似模型对输入特征的输出。我们的方法可以表示为 LRP 解释的组合，这些解释在之前的作品中已被证明可以扩展到高度非线性模型。通过大量的实验，我们证明 BiLRP 可以稳健地解释复杂的相似性模型，例如基于 VGG-16 深度神经网络特征构建的模型。此外，我们将我们的方法应用于数字人文中的一个开放问题：详细评估历史文献（例如天文表）之间的相似性。 BiLRP 再次提供了洞察力，并将可验证性带入高度工程化和针对特定问题的相似性模型中。