Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations
This addresses the problem of modeling evolving graph structures and node dynamics for researchers in graph representation learning, representing an incremental advancement by adapting neural controlled differential equations to graphs.
The paper tackles representation learning for dynamic graphs with temporal interactions by proposing Graph Neural Controlled Differential Equations (GN-CDEs), a continuous-time framework that jointly models node embeddings and structural dynamics, demonstrating effectiveness in capturing complex dynamics across various tasks.
This paper focuses on representation learning for dynamic graphs with temporal interactions. A fundamental issue is that both the graph structure and the nodes own their own dynamics, and their blending induces intractable complexity in the temporal evolution over graphs. Drawing inspiration from the recent progress of physical dynamic models in deep neural networks, we propose Graph Neural Controlled Differential Equations (GN-CDEs), a continuous-time framework that jointly models node embeddings and structural dynamics by incorporating a graph enhanced neural network vector field with a time-varying graph path as the control signal. Our framework exhibits several desirable characteristics, including the ability to express dynamics on evolving graphs without piecewise integration, the capability to calibrate trajectories with subsequent data, and robustness to missing observations. Empirical evaluation on a range of dynamic graph representation learning tasks demonstrates the effectiveness of our proposed approach in capturing the complex dynamics of dynamic graphs.