Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting

TL;DR

This paper introduces SEARCH, a scalable automated framework for designing deep learning models for correlated time series forecasting, outperforming manual and existing automated methods in accuracy and scalability.

Contribution

The paper presents a joint architecture-hyperparameter search method with an efficient ranking mechanism, advancing automated CTS forecasting.

Findings

SEARCH outperforms manual and existing automated models.

It scales effectively to large-scale CTS datasets.

It reduces manual effort in model design.

Abstract

Sensors in cyber-physical systems often capture interconnected processes and thus emit correlated time series (CTS), the forecasting of which enables important applications. The key to successful CTS forecasting is to uncover the temporal dynamics of time series and the spatial correlations among time series. Deep learning-based solutions exhibit impressive performance at discerning these aspects. In particular, automated CTS forecasting, where the design of an optimal deep learning architecture is automated, enables forecasting accuracy that surpasses what has been achieved by manual approaches. However, automated CTS solutions remain in their infancy and are only able to find optimal architectures for predefined hyperparameters and scale poorly to large-scale CTS. To overcome these limitations, we propose SEARCH, a joint, scalable framework, to automatically devise effective CTS forecasting models. Specifically, we encode each candidate architecture and accompanying hyperparameters into a joint graph representation. We introduce an efficient Architecture-Hyperparameter Comparator (AHC) to rank all architecture-hyperparameter pairs, and we then further evaluate the top-ranked pairs to select a final result. Extensive experiments on six benchmark datasets demonstrate that SEARCH not only eliminates manual efforts but also is capable of better performance than manually designed and existing automatically designed CTS models. In addition, it shows excellent scalability to large CTS.