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

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-05
Main Authors: Zheng, Dong, Jiang, Renhe, Gao, Haotian, Liu, Hangchen, Deng, Jinliang, Wen, Qingsong, Song, Xuan
Format: Article
Language:English
Subjects:
Clustering
Forecasting
Heterogeneity
Learning
Parameters
Time series
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422