MMODELYST
Papers/One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification
PAP

One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification

May 11, 2026

arXiv
Abstract

Neural Flows efficiently model irregular multivariate time series by directly learning ODE solution trajectories with neural networks, bypassing step-by-step numerical solvers. Despite their efficiency, many existing approaches treat variables independently, leaving inter-variable interactions underexplored. Moreover, their one-step mapping makes interaction modeling inherently challenging, as it removes the iterative refinement of interactions during learning. To address this challenge, we propose one-step Graph-Structured Neural Flows (GSNF), which introduce two auxiliary-trajectory self-supervision strategies to strengthen interaction learning: (i) interaction-aware trajectory generation via re-initialization, which induces trajectory divergence to expose graph-induced interactions, with a theoretically derived lower bound on divergence; and (ii) reverse-time trajectory generation, which enforces forward-backward consistency to regularize graph learning, enabled by flow invertibility. Experiments on five real-world datasets show that GSNF achieves state-of-the-art classification performance with highly competitive training time and memory usage.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Mengzhou Gao, Kaiwei Wang, Pengfei Jiao
Your notes (browser-local)
saved
arXiv:2605.10179