Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting
This addresses the need for automated, transferable forecasting models in intelligent applications, though it appears incremental as it builds on existing neural architecture search and graph learning techniques.
The paper tackles the challenge of multivariate time series forecasting by proposing a scale-aware neural architecture search framework that automatically captures multi-scale temporal patterns and inter-variable dependencies without prior knowledge, achieving promising performance on two real-world datasets.
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.