Functional Latent Dynamics for Irregularly Sampled Time Series Forecasting

TL;DR

This paper introduces Functional Latent Dynamics (FLD), a novel approach for irregularly sampled time series forecasting that outperforms ODE-based models in accuracy and efficiency by using simple curves to model continuous latent states.

Contribution

The paper proposes FLD, a new model that avoids complex ODE solving by using simple curves for continuous latent states, improving speed and memory efficiency.

Findings

FLD outperforms ODE-based models in accuracy.

FLD reduces inference time by an order of magnitude.

FLD requires less memory and computational resources.

Abstract

Irregularly sampled time series with missing values are often observed in multiple real-world applications such as healthcare, climate and astronomy. They pose a significant challenge to standard deep learning models that operate only on fully observed and regularly sampled time series. In order to capture the continuous dynamics of the irregular time series, many models rely on solving an Ordinary Differential Equation (ODE) in the hidden state. These ODE-based models tend to perform slow and require large memory due to sequential operations and a complex ODE solver. As an alternative to complex ODE-based models, we propose a family of models called Functional Latent Dynamics (FLD). Instead of solving the ODE, we use simple curves which exist at all time points to specify the continuous latent state in the model. The coefficients of these curves are learned only from the observed values in the time series ignoring the missing values. Through extensive experiments, we demonstrate that FLD achieves better performance compared to the best ODE-based model while reducing the runtime and memory overhead. Specifically, FLD requires an order of magnitude less time to infer the forecasts compared to the best performing forecasting model.