Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

TL;DR

This paper introduces SNAS4MTF, a scale-aware neural architecture search framework that effectively captures multi-scale temporal patterns and variable dependencies for multivariate time series forecasting, reducing the need for domain expertise.

Contribution

The paper proposes a novel end-to-end framework combining multi-scale decomposition, adaptive graph learning, and neural architecture search for improved MTS forecasting.

Findings

SNAS4MTF outperforms state-of-the-art methods on real-world datasets.

The framework effectively captures multi-scale temporal patterns.

Adaptive graph learning infers variable dependencies without prior knowledge.

Abstract

Multivariate time series (MTS) forecasting has attracted much attention in many intelligent applications. It is not a trivial task, as we need to consider both intra-variable dependencies and inter-variable dependencies. However, existing works are designed for specific scenarios, and require much domain knowledge and expert efforts, which is difficult to transfer between different scenarios. In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF). A multi-scale decomposition module transforms raw time series into multi-scale sub-series, which can preserve multi-scale temporal patterns. An adaptive graph learning module infers the different inter-variable dependencies under different time scales without any prior knowledge. For MTS forecasting, a search space is designed to capture both intra-variable dependencies and inter-variable dependencies at each time scale. The multi-scale decomposition, adaptive graph learning, and neural architecture search modules are jointly learned in an end-to-end framework. Extensive experiments on two real-world datasets demonstrate that SNAS4MTF achieves a promising performance compared with the state-of-the-art methods.