Temporal Graph ODEs for Irregularly-Sampled Time Series

TL;DR

The paper introduces TG-ODE, a novel framework that models irregularly-sampled temporal graph data using differential equations, enabling better learning of continuous dynamics in real-world scenarios.

Contribution

It presents the first continuous-time graph learning model that handles irregular sampling intervals using ODEs, advancing temporal graph representation learning.

Findings

Achieves state-of-the-art performance on irregular graph stream benchmarks.

Effectively models continuous dynamics in irregularly-sampled data.

Outperforms existing methods designed for regularly sampled graphs.

Abstract

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.