Unlocking the Power of LSTM for Long Term Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kong, Yaxuan, Wang, Zepu, Nie, Yuqi, Zhou, Tian, Zohren, Stefan, Liang, Yuxuan, Sun, Peng, Wen, Qingsong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912243197673472
author Kong, Yaxuan
Wang, Zepu
Nie, Yuqi
Zhou, Tian
Zohren, Stefan
Liang, Yuxuan
Sun, Peng
Wen, Qingsong
author_facet Kong, Yaxuan
Wang, Zepu
Nie, Yuqi
Zhou, Tian
Zohren, Stefan
Liang, Yuxuan
Sun, Peng
Wen, Qingsong
contents Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10006
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unlocking the Power of LSTM for Long Term Time Series Forecasting
Kong, Yaxuan
Wang, Zepu
Nie, Yuqi
Zhou, Tian
Zohren, Stefan
Liang, Yuxuan
Sun, Peng
Wen, Qingsong
Machine Learning
Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model.
title Unlocking the Power of LSTM for Long Term Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2408.10006