cs-net: structural approach to time-series forecasting for high-dimensional feature space data with limited observations

TL;DR

This paper introduces a novel attention-based CNN approach for high-dimensional multivariate time-series forecasting, addressing training time and memory constraints, and demonstrating top performance in a challenge setting.

Contribution

The paper presents a flexible feature extraction technique inspired by Hilbert space basis change, optimized for high-dimensional forecasting with limited observations.

Findings

Achieved 1st and 2nd place in the ATD 2022 Challenge.

Demonstrated superior performance on the GDELT Dataset.

Effective handling of high-dimensional data with limited training resources.

Abstract

In recent years, deep-learning-based approaches have been introduced to solving time-series forecasting-related problems. These novel methods have demonstrated impressive performance in univariate and low-dimensional multivariate time-series forecasting tasks. However, when these novel methods are used to handle high-dimensional multivariate forecasting problems, their performance is highly restricted by a practical training time and a reasonable GPU memory configuration. In this paper, inspired by a change of basis in the Hilbert space, we propose a flexible data feature extraction technique that excels in high-dimensional multivariate forecasting tasks. Our approach was originally developed for the National Science Foundation (NSF) Algorithms for Threat Detection (ATD) 2022 Challenge. Implemented using the attention mechanism and Convolutional Neural Networks (CNN) architecture, our method demonstrates great performance and compatibility. Our models trained on the GDELT Dataset finished 1st and 2nd places in the ATD sprint series and hold promise for other datasets for time series forecasting.