Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting

TL;DR

This paper introduces HimNet, a novel spatiotemporal forecasting model that captures heterogeneity through embeddings and meta-parameter learning, achieving state-of-the-art results and interpretability.

Contribution

The paper proposes a heterogeneity-informed meta-parameter learning scheme and a new HimNet model for improved spatiotemporal forecasting.

Findings

Achieves state-of-the-art performance on five benchmarks.

Demonstrates superior interpretability.

Effectively captures spatiotemporal heterogeneity.

Abstract

Spatiotemporal time series forecasting plays a key role in a wide range of real-world applications. While significant progress has been made in this area, fully capturing and leveraging spatiotemporal heterogeneity remains a fundamental challenge. Therefore, we propose a novel Heterogeneity-Informed Meta-Parameter Learning scheme. Specifically, our approach implicitly captures spatiotemporal heterogeneity through learning spatial and temporal embeddings, which can be viewed as a clustering process. Then, a novel spatiotemporal meta-parameter learning paradigm is proposed to learn spatiotemporal-specific parameters from meta-parameter pools, which is informed by the captured heterogeneity. Based on these ideas, we develop a Heterogeneity-Informed Spatiotemporal Meta-Network (HimNet) for spatiotemporal time series forecasting. Extensive experiments on five widely-used benchmarks demonstrate our method achieves state-of-the-art performance while exhibiting superior interpretability. Our code is available at https://github.com/XDZhelheim/HimNet.