Continuous Temporal Graph Networks for Event-Based Graph Data
This work addresses the challenge of continuous temporal modeling for dynamic graphs, which is incremental as it builds on existing discrete methods by generalizing them with a continuous framework.
The paper tackled the problem of modeling continuous-time dynamics in temporal graph data, proposing Continuous Temporal Graph Networks (CTGNs) that use neural ODEs to capture node representation dynamics, and demonstrated effectiveness in transductive and inductive tasks over competitive baselines.
There has been an increasing interest in modeling continuous-time dynamics of temporal graph data. Previous methods encode time-evolving relational information into a low-dimensional representation by specifying discrete layers of neural networks, while real-world dynamic graphs often vary continuously over time. Hence, we propose Continuous Temporal Graph Networks (CTGNs) to capture the continuous dynamics of temporal graph data. We use both the link starting timestamps and link duration as evolving information to model the continuous dynamics of nodes. The key idea is to use neural ordinary differential equations (ODE) to characterize the continuous dynamics of node representations over dynamic graphs. We parameterize ordinary differential equations using a novel graph neural network. The existing dynamic graph networks can be considered as a specific discretization of CTGNs. Experiment results on both transductive and inductive tasks demonstrate the effectiveness of our proposed approach over competitive baselines.