Learning to infer missing links is one of the fundamental tasks in the knowledge graph. Instead of reasoning based on separate paths in the existing methods, in this paper, we propose a new model, Sequential Relational Graph Convolutional Network (SRGCN), which treats the multiple paths between an entity pair as a sequence of subgraphs. Specifically, to reason the relationship between two entities, we first construct a graph for the entities based on the knowledge graph and serialize the graph to a sequence. For each hop in the sequence, Relational Graph Convolutional Network (R-GCN) is then applied to update the embeddings of the entities. The updated embedding of the tail entity contains information of the entire graph, hence the relationship between two entities can be inferred from it. Compared to the existing approaches that deal with paths separately, SRGCN treats the graph as a whole, which can encode structural information and interactions between paths better. Experiments show that SRGCN outperforms path-based baselines on both link and fact prediction tasks. We also show that SRGCN is highly efficient in the sense that only one epoch of training is enough to achieve high accuracy, and even partial datasets can lead to competitive performance.

学习推断缺失的链接是知识图中的基本任务之一。与现有方法中基于单独路径的推理不同，在本文中，我们提出了一种新模型，即序列关系图卷积网络（SRGCN），它将实体对之间的多条路径视为子图序列。具体来说，为了推理两个实体之间的关系，我们首先根据知识图为实体构建一个图，并将图序列化为一个序列。对于序列中的每一跳，然后应用关系图卷积网络 (R-GCN) 来更新实体的嵌入。尾部实体的更新嵌入包含整个图的信息，因此可以从中推断出两个实体之间的关系。与现有的单独处理路径的方法相比，SRGCN 将图视为一个整体，可以更好地编码路径之间的结构信息和交互。实验表明，SRGCN 在链接和事实预测任务上都优于基于路径的基线。我们还表明 SRGCN 是高效的，因为只有一个训练时期就足以实现高精度，甚至部分数据集也可以带来有竞争力的表现。