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

TL;DR

The paper introduces GSNF, a novel neural flow model that captures inter-variable interactions in irregular multivariate time series through self-supervision strategies, achieving state-of-the-art classification.

Contribution

Proposes one-step Graph-Structured Neural Flows with self-supervision to enhance interaction modeling in irregular time series, addressing limitations of existing neural flow methods.

Findings

GSNF achieves state-of-the-art classification accuracy.

It maintains competitive training time and memory efficiency.

Theoretical lower bound on trajectory divergence is derived.

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.