Context-free graph grammars have shown a remarkable ability to model structures in real-world relational data. However, graph grammars lack the ability to capture time-changing phenomena since the left-to-right transitions of a production rule do not represent temporal change. In the present work, we describe dynamic vertex-replacement grammars (DyVeRG), which generalize vertex replacement grammars in the time domain by providing a formal framework for updating a learned graph grammar in accordance with modifications to its underlying data. We show that DyVeRG grammars can be learned from, and used to generate, real-world dynamic graphs faithfully while remaining human-interpretable. We also demonstrate their ability to forecast by computing dyvergence scores, a novel graph similarity measurement exposed by this framework.

翻译：上下文无关图语法已展现出对真实世界关系数据中结构建模的显著能力。然而，图语法无法捕捉随时间变化的现象，因为产生式规则的左至右转换并不代表时间变化。在本工作中，我们提出动态顶点替换语法（DyVeRG），该语法通过提供一种形式化框架，根据底层数据的修改来更新已学习的图语法，从而在时间域上推广了顶点替换语法。我们证明，DyVeRG语法可以从真实世界动态图中学习并用于生成忠实反映原始数据的图，同时保持人类可解释性。我们还展示了其通过计算dyvergence分数（该框架揭示的一种新型图相似性度量）进行预测的能力。