Graph Neural Ordinary Differential Equations
This provides a novel continuous-depth framework for graph neural networks that could benefit researchers and practitioners working with dynamic graph data.
The authors tackled the problem of modeling continuous-depth relationships in graph-structured data by introducing Graph Neural Ordinary Differential Equations (GDEs), which blend discrete topological structures with differential equations. Results showed that GDEs offer computational advantages in static settings and improve performance in dynamic settings by exploiting underlying dynamics geometry.
We introduce the framework of continuous--depth graph neural networks (GNNs). Graph neural ordinary differential equations (GDEs) are formalized as the counterpart to GNNs where the input-output relationship is determined by a continuum of GNN layers, blending discrete topological structures and differential equations. The proposed framework is shown to be compatible with various static and autoregressive GNN models. Results prove general effectiveness of GDEs: in static settings they offer computational advantages by incorporating numerical methods in their forward pass; in dynamic settings, on the other hand, they are shown to improve performance by exploiting the geometry of the underlying dynamics.