Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

TL;DR

This paper introduces three stable classes of Neural SDEs designed to handle irregular time series data with missing values, demonstrating robustness and improved performance across multiple tasks and datasets.

Contribution

The paper proposes three novel stable Neural SDE classes and provides a rigorous analysis of their robustness and stability in real-world irregular time series applications.

Findings

Effective handling of irregular sampling and missing data

Robust performance under distribution shifts

Prevention of overfitting in diverse datasets

Abstract

Irregular sampling intervals and missing values in real-world time series data present challenges for conventional methods that assume consistent intervals and complete data. Neural Ordinary Differential Equations (Neural ODEs) offer an alternative approach, utilizing neural networks combined with ODE solvers to learn continuous latent representations through parameterized vector fields. Neural Stochastic Differential Equations (Neural SDEs) extend Neural ODEs by incorporating a diffusion term, although this addition is not trivial, particularly when addressing irregular intervals and missing values. Consequently, careful design of drift and diffusion functions is crucial for maintaining stability and enhancing performance, while incautious choices can result in adverse properties such as the absence of strong solutions, stochastic destabilization, or unstable Euler discretizations, significantly affecting Neural SDEs' performance. In this study, we propose three stable classes of Neural SDEs: Langevin-type SDE, Linear Noise SDE, and Geometric SDE. Then, we rigorously demonstrate their robustness in maintaining excellent performance under distribution shift, while effectively preventing overfitting. To assess the effectiveness of our approach, we conduct extensive experiments on four benchmark datasets for interpolation, forecasting, and classification tasks, and analyze the robustness of our methods with 30 public datasets under different missing rates. Our results demonstrate the efficacy of the proposed method in handling real-world irregular time series data.