Temporal Graph ODEs for Irregularly-Sampled Time Series

arXiv:2404.19508v1 Announce Type: new
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 …

abstract arxiv continuous cs.lg differential differential equation dynamics equation graph graph representation modern networks ordinary representation representation learning series social social networks systems temporal time series type