AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version

TL;DR

AutoCTS automates the design of correlated time series forecasting models by automatically discovering optimal spatio-temporal block architectures and connections, outperforming human-designed models on benchmark datasets.

Contribution

It introduces a joint search strategy over micro and macro architecture spaces for CTS forecasting, enabling automatic discovery of heterogeneous spatio-temporal models.

Findings

AutoCTS outperforms state-of-the-art models on 8 benchmark datasets.

The method effectively discovers diverse and high-performing architectures.

Automated architecture search reduces manual design effort and improves forecasting accuracy.

Abstract

Correlated time series (CTS) forecasting plays an essential role in many cyber-physical systems, where multiple sensors emit time series that capture interconnected processes. Solutions based on deep learning that deliver state-of-the-art CTS forecasting performance employ a variety of spatio-temporal (ST) blocks that are able to model temporal dependencies and spatial correlations among time series. However, two challenges remain. First, ST-blocks are designed manually, which is time consuming and costly. Second, existing forecasting models simply stack the same ST-blocks multiple times, which limits the model potential. To address these challenges, we propose AutoCTS that is able to automatically identify highly competitive ST-blocks as well as forecasting models with heterogeneous ST-blocks connected using diverse topologies, as opposed to the same ST-blocks connected using simple stacking. Specifically, we design both a micro and a macro search space to model possible architectures of ST-blocks and the connections among heterogeneous ST-blocks, and we provide a search strategy that is able to jointly explore the search spaces to identify optimal forecasting models. Extensive experiments on eight commonly used CTS forecasting benchmark datasets justify our design choices and demonstrate that AutoCTS is capable of automatically discovering forecasting models that outperform state-of-the-art human-designed models. This is an extended version of ``AutoCTS: Automated Correlated Time Series Forecasting'', to appear in PVLDB 2022.