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 Additionally, we apply our method to an open problem in digital humanities: detailed assessment of similarity between historical documents, such as astronomical tables.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性模型

许多学习算法，例如内核机器、最近邻、聚类或异常检测，都是基于距离或相似性。在将相似性用于训练实际的机器学习模型之前，我们想验证它们是否与数据中有意义的模式相关联。在本文中，我们建议通过使用解释 。我们开发了 BiLRP，这是一种可扩展且具有理论基础的方法，用于系统地分解已经训练过的深度相似性模型在输入特征对上的输出。我们的方法可以表示为 LRP 解释的组合，这些解释在以前的工作中被证明可以扩展到高度非线性模型。通过一系列广泛的实验，我们证明 BiLRP 可以稳健地解释复杂的相似性模型，例如，建立在 VGG-16 深度神经网络特征上。此外，我们将我们的方法应用于数字人文学科中的一个开放问题：详细评估历史文件之间的相似性，例如天文表。在这里，BiLRP 再次提供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。