论文标题
图形神经距离学习与图形 - 伯特
Graph Neural Distance Metric Learning with Graph-Bert
论文作者
论文摘要
图距离度量学习是许多图形学习问题的基础，例如图形聚类，图形分类和图形匹配。图形距离指标（或图内核）学习的现有研究工作无法分别维持此类指标的基本属性，例如非负，不可分辨物，对称性和三角形不平等的身份。在本文中，我们将介绍一种新的基于图形神经网络的距离度量学习方法，即GB-Distance（基于图形 - 伯特的神经距离）。 GB-Distance仅基于注意机制，可以根据预训练的图形模型有效地学习图形实例表示。与现有的监督/无监督指标不同，可以以半监督的方式有效地学习GB距离。此外，GB距离还可以维持上述距离度量基本属性。已经在几个基准图数据集上进行了广泛的实验，结果表明，GB距离可以超越现有的基线方法，尤其是基于最新的图形神经网络模型的图形指标，并且在计算图形距离方面存在显着差距。
Graph distance metric learning serves as the foundation for many graph learning problems, e.g., graph clustering, graph classification and graph matching. Existing research works on graph distance metric (or graph kernels) learning fail to maintain the basic properties of such metrics, e.g., non-negative, identity of indiscernibles, symmetry and triangle inequality, respectively. In this paper, we will introduce a new graph neural network based distance metric learning approaches, namely GB-DISTANCE (GRAPH-BERT based Neural Distance). Solely based on the attention mechanism, GB-DISTANCE can learn graph instance representations effectively based on a pre-trained GRAPH-BERT model. Different from the existing supervised/unsupervised metrics, GB-DISTANCE can be learned effectively in a semi-supervised manner. In addition, GB-DISTANCE can also maintain the distance metric basic properties mentioned above. Extensive experiments have been done on several benchmark graph datasets, and the results demonstrate that GB-DISTANCE can out-perform the existing baseline methods, especially the recent graph neural network model based graph metrics, with a significant gap in computing the graph distance.
