There has been an increasing interest in inferring future links on temporal knowledge graphs (KG). While links on temporal KGs vary continuously over time, the existing approaches model the temporal KGs in discrete state spaces. To this end, we propose a novel continuum model by extending the idea of neural ordinary differential equations (ODEs) to multi-relational graph convolutional networks. The proposed model preserves the continuous nature of dynamic multi-relational graph data and encodes both temporal and structural information into continuous-time dynamic embeddings. In addition, a novel graph transition layer is applied to capture the transitions on the dynamic graph, i.e., edge formation and dissolution. We perform extensive experiments on five benchmark datasets for temporal KG reasoning, showing our model's superior performance on the future link forecasting task.
翻译:人们越来越有兴趣在时间知识图(KG)上推断未来联系。时间知识图(KG)上的链接随着时间的变化而不断变化,而现有的方法则在离散的状态空间中模拟时间KG。为此,我们提出一个新的连续模式,将神经普通差异方程式(ODEs)的概念扩大到多关系图进化网络。拟议的模型保留了动态多关系图数据的连续性,并将时间和结构信息编码为连续时间动态嵌入。此外,还应用了一个新的图形转换层来捕捉动态图的转变,即边缘形成和解体。我们广泛试验了用于时间KG推理的五个基准数据集,展示了我们模型在未来链接预测任务的优异性表现。