Learning Dynamic Graph Embeddings With Neural Controlled Differential Equations

Tiexin Qin

doi:10.1109/TPAMI.2025.3617660

Learning Dynamic Graph Embeddings With Neural Controlled Differential Equations

2025-10-03

0

PRE

AI

DOI：10.1109/TPAMI.2025.3617660

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Dynamic graph

embedding learning

graph neural network

controlled differential equations

Learning Dynamic Graph Embeddings With Neural Controlled Differential Equations

Abstract

Journal

Organization