WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series

Fuhao Yang; Xin Li; Min Wang; Hongyu Zang; Wei Pang; Mingzhong Wang

doi:10.1609/aaai.v37i9.26276

Back

WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series

Conference paper

Peer reviewed

WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series

Fuhao Yang, Xin Li, Min Wang, Hongyu Zang, Wei Pang and Mingzhong Wang

Proceedings of the AAAI Conference on Artificial Intelligence, Vol.37(9), pp.10754-10761

Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, 37th (Washington, D.C., United States, 07-Feb-2023–14-Feb-2023)

AAAI Press

2023

DOI: https://doi.org/10.1609/aaai.v37i9.26276

Files and links (1)

url

https://doi.org/10.1609/aaai.v37i9.26276View

Published Version

Abstract

Artificial intelligence

time-series/data streams

deep neural architectures

graph-based machine learning

representation learning

Multivariate time series (MTS) analysis and forecasting are crucial in many real-world applications, such as smart traffic management and weather forecasting. However, most existing work either focuses on short sequence forecasting or makes predictions predominantly with time domain features, which is not effective at removing noises with irregular frequencies in MTS. Therefore, we propose WaveForM, an end-to-end graph enhanced Wavelet learning framework for long sequence FORecasting of MTS. WaveForM first utilizes Discrete Wavelet Transform (DWT) to represent MTS in the wavelet domain, which captures both frequency and time domain features with a sound theoretical basis. To enable the effective learning in the wavelet domain, we further propose a graph constructor, which learns a global graph to represent the relationships between MTS variables, and graph-enhanced prediction modules, which utilize dilated convolution and graph convolution to capture the correlations between time series and predict the wavelet coefficients at different levels. Extensive experiments on five real-world forecasting datasets show that our model can achieve considerable performance improvement over different prediction lengths against the most competitive baseline of each dataset.

Details

Title: WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series
Authors: Fuhao Yang (Author) - Beijing Institute of Technology
Xin Li (Author) - Beijing Institute of Technology
Min Wang (Author) - Beijing Institute of Technology
Hongyu Zang (Author) - Beijing Institute of Technology
Wei Pang (Author) - Heriot-Watt University
Mingzhong Wang (Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Publication details: Proceedings of the AAAI Conference on Artificial Intelligence, Vol.37(9), pp.10754-10761
Conference details: Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, 37th (Washington, D.C., United States, 07-Feb-2023–14-Feb-2023)
Publisher: AAAI Press
Date published: 2023
DOI: 10.1609/aaai.v37i9.26276
ISSN: 2374-3468
ISBN: 9781577358800
Organisation Unit: School of Science, Technology and Engineering
Language: English
Record Identifier: 99741198902621
Output Type: Conference paper

Metrics

37 Record Views

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Web Of Science research areas: Computer Science, Artificial Intelligence; Computer Science, Theory & Methods; Mathematics, Applied