监督领域自适应：我们一直都在做图形嵌入吗？（CS LG）---刘持诚

当训练数据和测试数据的分布不同时，机器学习模型的性能往往会受到影响。领域自适应就是缩小数据集之间分布差距的过程。在本文中，我们展示了现有的领域适配方法可以被表述为 Graph Embedding 方法，其中来自源域和目标域的样本的域标签被纳入到用于嵌入的本征图（intrinsic graph）和惩罚图（penalty graph） 的结构中。为此，我们定义了三种最先进的监督领域适应方法的底层本征图和惩罚图。此外，我们提出了通过图嵌入的领域适应方法（DAGE），作为监督域适应的一般解决方案，它可以与各种图结构相结合，用于编码源域和目标域数据之间的成对关系。此外，我们还强调了一些通用性和可重现性问题，这些问题与一些实验设置有关。这些实验设置通常用于评估领域自适应方法的性能。我们提出了一个新的评估设置，以更准确地评估和比较不同的监督领域自适应方法。而且我们也在文中报告了在标准基准数据集 Office31 和 MNIST-USPS 上的实验。

原文题目：Supervised Domain Adaptation: Were we doing Graph Embedding all along?

原文：The performance of machine learning models tends to suffer when the distributions of the training and test data differ. Domain Adaptation is the process of closing the distribution gap between datasets. In this paper, we show that existing Domain Adaptation methods can be formulated as Graph Embedding methods in which the domain labels of samples coming from the source and target domains are incorporated into the structure of the intrinsic and penalty graphs used for the embedding. To this end, we define the underlying intrinsic and penalty graphs for three state-of-the-art supervised domain adaptation methods. In addition, we propose the Domain Adaptation via Graph Embedding (DAGE) method as a general solution for supervised Domain Adaptation, that can be combined with various graph structures for encoding pair-wise relationships between source and target domain data. Moreover, we highlight some generalisation and reproducibility issues related to the experimental setup commonly used to evaluate the performance of Domain Adaptation methods. We propose a new evaluation setup for more accurately assessing and comparing different supervised DA methods, and report experiments on the standard benchmark datasets Office31 and MNIST-USPS.

原文作者：Lukas Hedegaard, Omar Ali Sheikh-Omar, Alexandros Iosifidis

原文地址：https://arxiv.org/abs/2004.11262