Forecasting Irregularly Sampled Time Series using Graphs

TL;DR

This paper introduces GraFITi, a graph-based model for forecasting irregularly sampled time series with missing data, achieving higher accuracy and faster computation than existing methods.

Contribution

The paper presents a novel graph neural network approach that converts time series into a sparsity structure graph for improved forecasting of irregularly sampled data.

Findings

GraFITi improves forecasting accuracy by up to 17%.

GraFITi reduces runtime by up to 5 times.

Validated on real-world and synthetic datasets.

Abstract

Forecasting irregularly sampled time series with missing values is a crucial task for numerous real-world applications such as healthcare, astronomy, and climate sciences. State-of-the-art approaches to this problem rely on Ordinary Differential Equations (ODEs) which are known to be slow and often require additional features to handle missing values. To address this issue, we propose a novel model using Graphs for Forecasting Irregularly Sampled Time Series with missing values which we call GraFITi. GraFITi first converts the time series to a Sparsity Structure Graph which is a sparse bipartite graph, and then reformulates the forecasting problem as the edge weight prediction task in the graph. It uses the power of Graph Neural Networks to learn the graph and predict the target edge weights. GraFITi has been tested on 3 real-world and 1 synthetic irregularly sampled time series dataset with missing values and compared with various state-of-the-art models. The experimental results demonstrate that GraFITi improves the forecasting accuracy by up to 17% and reduces the run time up to 5 times compared to the state-of-the-art forecasting models.