Temporal Graph ODEs for Irregularly-Sampled Time Series

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.

Authors

• Alessio Gravina University of Pisa
• Daniele Zambon
• Davide Bacciu University of Pisa
• Cesare Alippi The Swiss AI Lab IDSIA, Università della Svizzera italiana Politecnico di Milano

Keywords

• Machine Learning: ML: Deep learning architectures
• Machine Learning: ML: Sequence and graph learning
• Machine Learning: ML: Time series and data streams