Learning Differential Operators for Interpretable Time Series Modeling

Abstract

Modeling sequential patterns from data is at the core of various time series forecasting tasks. Deep learning models have greatly outperformed many traditional models, but these black-box models generally lack explainability in prediction and decision making. To reveal the underlying trend with understandable mathematical expressions, scientists and economists tend to use partial differential equations (PDEs) to explain the highly nonlinear dynamics of sequential patterns. However, it usually requires domain expert knowledge and a series of simplified assumptions, which is not always practical and can deviate from the ever-changing world. Is it possible to learn the differential relations from data dynamically to explain the time-evolving dynamics? In this work, we propose an learning framework that can automatically obtain interpretable PDE models from sequential data. Particularly, this framework is comprised of learnable differential blocks, named $P$-blocks, which is proved to be able to approximate any time-evolving complex continuous functions in theory. Moreover, to capture the dynamics shift, this framework introduces a meta-learning controller to dynamically optimize the hyper-parameters of a hybrid PDE model. Extensive experiments on times series forecasting of financial, engineering, and health data show that our model can provide valuable interpretability and achieve comparable performance to state-of-the-art models. From empirical studies, we find that learning a few differential operators may capture the major trend of sequential dynamics without massive computational complexity.

arXiv commentPublished in ACM SIGKDD 2022

References in corpus (12)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• Time Series Forecasting With Deep Learning: A Survey
• Solving high-dimensional partial differential equations using deep learning
• Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
• Deep-learning of Parametric Partial Differential Equations from Sparse and Noisy Data

Cited by in corpus (4)

• A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecasting
• Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
• Physics-Guided Discovery of Highly Nonlinear Parametric Partial Differential Equations
• Deep Stable Representation Learning on Electronic Health Records