PIETS: Parallelised Irregularity Encoders for Forecasting with Heterogeneous Time-Series

TL;DR

PIETS is a novel neural architecture designed to effectively model and forecast heterogeneous and irregular multi-source time-series data, outperforming existing methods in real-world COVID-19 datasets.

Contribution

The paper introduces PIETS, a new architecture with irregularity encoders, parallelised neural networks, and attention mechanisms for improved multi-source time-series forecasting.

Findings

PIETS outperforms state-of-the-art methods in COVID-19 data prediction.

The architecture effectively models heterogeneous and irregular time-series.

PIETS accelerates convergence and leverages all available information.

Abstract

Heterogeneity and irregularity of multi-source data sets present a significant challenge to time-series analysis. In the literature, the fusion of multi-source time-series has been achieved either by using ensemble learning models which ignore temporal patterns and correlation within features or by defining a fixed-size window to select specific parts of the data sets. On the other hand, many studies have shown major improvement to handle the irregularity of time-series, yet none of these studies has been applied to multi-source data. In this work, we design a novel architecture, PIETS, to model heterogeneous time-series. PIETS has the following characteristics: (1) irregularity encoders for multi-source samples that can leverage all available information and accelerate the convergence of the model; (2) parallelised neural networks to enable flexibility and avoid information overwhelming; and (3) attention mechanism that highlights different information and gives high importance to the most related data. Through extensive experiments on real-world data sets related to COVID-19, we show that the proposed architecture is able to effectively model heterogeneous temporal data and outperforms other state-of-the-art approaches in the prediction task.