Irregularly-Sampled Time Series Modeling with Spline Networks

TL;DR

This paper introduces a novel neural network approach that directly operates on spline representations of irregularly-sampled time series, improving efficiency and accuracy in classification and forecasting tasks.

Contribution

The paper proposes spline-based neural network layers that process continuous-time interpolations directly, enabling effective modeling of irregular time series without grid sampling.

Findings

Competitive accuracy with existing methods

Enhanced computational efficiency

Effective handling of irregular sampling and missing data

Abstract

Observations made in continuous time are often irregular and contain the missing values across different channels. One approach to handle the missing data is imputing it using splines, by fitting the piecewise polynomials to the observed values. We propose using the splines as an input to a neural network, in particular, applying the transformations on the interpolating function directly, instead of sampling the points on a grid. To do that, we design the layers that can operate on splines and which are analogous to their discrete counterparts. This allows us to represent the irregular sequence compactly and use this representation in the downstream tasks such as classification and forecasting. Our model offers competitive performance compared to the existing methods both in terms of the accuracy and computation efficiency.