Irregularly-Sampled Time Series Modeling with Spline Networks

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 n...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Marin Biloš, Ramneantu, Emanuel, Günnemann, Stephan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 19.10.2022
Subjects
Missing data
Neural networks
Polynomials
Spline functions
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422