One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification
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.
Cite
@article{arxiv.2605.10179,
title = {One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification},
author = {Mengzhou Gao and Kaiwei Wang and Pengfei Jiao},
journal= {arXiv preprint arXiv:2605.10179},
year = {2026}
}