Temporal Graph ODEs for Irregularly-Sampled Time Series
This addresses a limitation in graph representation learning for real-world applications with sporadic observations, but it is incremental as it builds on existing ODE methods for graphs.
The paper tackles the problem of learning from irregularly-sampled temporal graph data, such as social networks, by introducing the Temporal Graph ODE framework, which achieves state-of-the-art performance on graph benchmarks.
Modern graph representation learning works mostly under the assumption of dealing with regularly sampled temporal graph snapshots, which is far from realistic, e.g., social networks and physical systems are characterized by continuous dynamics and sporadic observations. To address this limitation, we introduce the Temporal Graph Ordinary Differential Equation (TG-ODE) framework, which learns both the temporal and spatial dynamics from graph streams where the intervals between observations are not regularly spaced. We empirically validate the proposed approach on several graph benchmarks, showing that TG-ODE can achieve state-of-the-art performance in irregular graph stream tasks.