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

2026-05-11

AI Summary

This work addresses the limitations of existing neural flow methods in modeling irregular multivariate time series, which often neglect dynamic inter-variable interactions and struggle to capture such dependencies through a single-step mapping. To overcome these challenges, we propose Graph-Structured Neural Flows (GSNF), the first framework to integrate graph structures and self-supervised trajectory learning into a one-step neural flow architecture. GSNF enhances interaction modeling via two auxiliary strategies: interaction-aware trajectory generation with reinitialization and invertibility-based backward-time trajectory generation. We further derive a theoretical lower bound on trajectory divergence and incorporate forward–backward consistency regularization to guide graph learning. Experiments demonstrate that GSNF achieves state-of-the-art classification performance across five real-world datasets while maintaining training efficiency and low memory consumption.

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.

Problem

• irregular multivariate time series
• neural flows
• inter-variable interactions
• one-step mapping
• time series classification

Innovation

• Graph-Structured Neural Flows
• Irregular Time Series
• Self-Supervision
• Neural ODEs
• Interaction Modeling