MPM: Multi Patterns Memory Model for Short-Term Time Series Forecasting

Dezheng Wang

doi:10.1109/TKDE.2024.3490843

MPM: Multi Patterns Memory Model for Short-Term Time Series Forecasting

2025-01-01

0

PRE

AI

DOI：10.1109/TKDE.2024.3490843

Original

Original request for help

Save

Abstract

En 中文

Short-term time series forecasting is pivotal in various scientific and industrial fields. Recent advancements in deep learning-based technologies have significantly improved the efficiency and accuracy of short-term time series modeling. Despite advancements, current time short-term series forecasting methods typically emphasize modeling dependencies across time stamps but frequently overlook inter-variable dependencies, which is crucial for multivariate forecasting. We propose a multi patterns memory model discovering various dependency patterns for short-term multivariate time series forecasting to fill the gap. The proposed model is structured around two key components: the short-term memory block and the long-term memory block. These networks are distinctively characterized by their use of asymmetric convolution, each tailored to process the various spatial-temporal dependencies among data. Experimental results show that the proposed model demonstrates competitive performance over the other time series forecasting methods across five benchmark datasets, likely thanks to the asymmetric structure, which can effectively extract the underlying various spatial-temporal dependencies among data.

Keywords:

Time series analysis

Forecasting

Predictive models

Transformers

Long short term memory

Convolution

Computational modeling

Feature extraction

Data models

Attention mechanisms

Asymmetric convolution

multi patterns memory model

spatial-temporal dependency

time series forecasting

MPM: Multi Patterns Memory Model for Short-Term Time Series Forecasting

Abstract

Journal

Organization