This work considers the task of representation learning on the attributed relational graph (ARG). Both the nodes and edges in an ARG are associated with attributes/features allowing ARGs to encode rich structural information widely observed in real applications. Existing graph neural networks offer limited ability to capture complex interactions within local structural contexts, which hinders them from taking advantage of the expression power of ARGs. We propose Motif Convolution Module (MCM), a new motif-based graph representation learning technique to better utilize local structural information. The ability to handle continuous edge and node features is one of MCM's advantages over existing motif-based models. MCM builds a motif vocabulary in an unsupervised way and deploys a novel motif convolution operation to extract the local structural context of individual nodes, which is then used to learn higher-level node representations via multilayer perceptron and/or message passing in graph neural networks. When compared with other graph learning approaches to classifying synthetic graphs, our approach is substantially better in capturing structural context. We also demonstrate the performance and explainability advantages of our approach by applying it to several molecular benchmarks.
翻译:这项工作考虑了在配对关系图(ARG)上进行代表学习的任务。阿根廷的节点和边缘都与属性/特点有关,使阿根廷能够将实际应用中广泛观察到的丰富的结构信息编码起来。现有的图形神经网络在捕捉当地结构环境中的复杂互动方面能力有限,这妨碍了它们利用ARG的表达力。我们提议采用基于运动的基于运动的图解学习新技巧Motif模块(MCM),以更好地利用当地的结构信息。处理连续边缘和节点功能的能力是MCM相对于现有基于运动模型的优势之一。MCM以不受监督的方式构建了一种运动词汇,并运用了一种新型的图解变行动来提取单个节点的当地结构环境,而后者被用来通过多层透视和/或通过图形神经网络传递的信息来学习高层次的节点表达。与其他图表学习方法相比,我们的方法在捕捉结构环境方面要好得多。我们还展示了我们的方法的性能和解释性能,通过将它应用于若干个分子基准。