Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting
This addresses the core issue in multivariate time-series forecasting for real-world applications, representing an incremental improvement through a novel method for a known bottleneck.
The paper tackles the problem of modeling complex spatial-temporal patterns in multivariate time-series forecasting by developing SCNN, a framework that decouples data into structured components for more predictable dynamics, achieving superior performance over state-of-the-art models on three real-world datasets.
Multivariate time-series (MTS) forecasting is a paramount and fundamental problem in many real-world applications. The core issue in MTS forecasting is how to effectively model complex spatial-temporal patterns. In this paper, we develop a adaptive, interpretable and scalable forecasting framework, which seeks to individually model each component of the spatial-temporal patterns. We name this framework SCNN, as an acronym of Structured Component-based Neural Network. SCNN works with a pre-defined generative process of MTS, which arithmetically characterizes the latent structure of the spatial-temporal patterns. In line with its reverse process, SCNN decouples MTS data into structured and heterogeneous components and then respectively extrapolates the evolution of these components, the dynamics of which are more traceable and predictable than the original MTS. Extensive experiments are conducted to demonstrate that SCNN can achieve superior performance over state-of-the-art models on three real-world datasets. Additionally, we examine SCNN with different configurations and perform in-depth analyses of the properties of SCNN.